{ "id": "AIBD-0127", "title": "Physicians treated Joseph Coates’s POEMS syndrome with three drugs that an early Every Cure algorithm also ranked highly, allowing a later stem cell transplant and remission", "summary": "Mr. Joseph Coates received three drugs (i) that a consulting physician had considered and (ii) that Every Cure’s early drug-repurposing system had scored highly.", "date_observed": "2025-03-20", "date_basis": "source publication", "date_precision": "day", "benefit_status": null, "source_collection": null, "source_entry": null, "account": "In January 2024, Joseph Coates, 37, of Renton, Washington, was critically ill with POEMS syndrome. His heart and kidneys were failing, and he was too sick for a stem cell transplant. His partner, Tara Theobald, asked David Fajgenbaum of the University of Pennsylvania and Every Cure for help. Fajgenbaum considered three drugs used for multiple myeloma, a related disease. He later explained that an early Every Cure algorithm also scored those drugs highly for POEMS. He recommended carfilzomib, cyclophosphamide, and dexamethasone to Coates’s treating hematologist and oncologist, Wayne Gao, who agreed to administer them. Coates later reported that he responded within one or two weeks and left intensive care three weeks later. He recovered enough to receive a stem cell transplant and reported full remission five months after that transplant. The New York Times reported improvement within a week and transplant eligibility about four months later. A brief vignette in The Lancet Haematology describes a matching unnamed patient and labels the result unpublished data. The sources support a contribution from AI alongside the physicians’ judgment, but they do not establish the exact model release or isolate its effect on recovery.", "category": "benefit created", "unexpected": false, "purpose": "Every Cure uses AI to rank existing drugs as candidates for other diseases. Its early algorithms helped Fajgenbaum assess drugs that he had considered for Coates’s POEMS syndrome. The New Yorker notes that Every Cure does not usually make recommendations for individual patients.", "system": "Every Cure’s early drug-repurposing system", "model_version": null, "developer": "Every Cure (co-founded by David Fajgenbaum, University of Pennsylvania)", "deployer": "David Fajgenbaum (Every Cure / University of Pennsylvania); regimen administered by Wayne Gao, Coates's treating hematologist and oncologist", "location": "Renton, United States", "domain": "Healthcare - rare disease / drug repurposing", "segment": "Individual off-label treatment of a terminal POEMS syndrome patient", "benefit_type": "Improved Physical Health", "taxonomy_note": null, "registry_ids": { "oecd_aim": "2025-03-21-aa9f" }, "ratings": [ { "group": "personal", "depth": 5, "reason": "Coates was critically ill, too sick for a transplant, and facing hospice care. He reported that he began responding to the drug regimen within one or two weeks, later received a stem cell transplant, and reached full remission five months after that transplant. The reported benefit was life-preserving. The available evidence does not isolate AI’s contribution from clinical judgment, the drugs, supportive care, or the transplant." } ], "ai_role": { "status": "assessed", "statement": "Fajgenbaum said that he had considered three drugs used for multiple myeloma and that Every Cure’s AI algorithm also scored them highly for POEMS syndrome. In an earlier AAMC interview, he described reviewing the scores and recommending the drugs to Coates’s treating physician. Wayne Gao weighed the risks and administered the treatment. The AI therefore supported the physicians’ assessment of candidate drugs. The sources do not show that it independently devised the regimen or that the benefit would have been impossible without it. The Lancet Haematology commentary contains a brief vignette of a matching unnamed POEMS patient, explicitly labeled unpublished data. No detailed clinical case report, underlying medical records, or case-specific model output was located. The commentary names KGML-xDTD as one of several algorithms in Every Cure’s platform, but it does not establish which algorithm or release was used for Coates." }, "evidence": [ { "kind": "news report", "citation": "Morgan, K. (2025). Doctors Told Him He Was Going to Die. Then A.I. Saved His Life. The New York Times, March 20, 2025.", "title": "Doctors Told Him He Was Going to Die. Then A.I. Saved His Life.", "url": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "date": "2025-03-20", "written_by": "independent", "quote": null }, { "kind": "news report", "citation": "Khullar, D. (2025). Can A.I. Find Cures for Untreatable Diseases—Using Drugs We Already Have? The New Yorker, Open Questions, 15 July 2025.", "title": "Can A.I. Find Cures for Untreatable Diseases—Using Drugs We Already Have?", "url": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "date": "2025-07-15", "written_by": "independent", "quote": "used the organization's A.I. platform to recommend a combination of drugs normally used to treat a blood cancer: a steroid called dexamethasone; a chemotherapy called cyclophosphamide; an immunotherapy called carfilzomib." }, { "kind": "press release", "citation": "Every Cure. Repurposing Portfolio, “Carfilzomib-cyclophosphamide-dexamethasone for POEMS syndrome.”", "title": "Repurposing Portfolio", "url": "https://everycure.org/portfolio/", "date": null, "written_by": "makers", "quote": "carfilzomib-cyclophosphamide-dexamethasone was administered to a POEMS patient in January 2024 who was getting ready to go onto hospice care, which ultimately saved his life" }, { "kind": "report", "citation": "Every Cure. 2025 Annual Report, “Joseph,” p. 15.", "title": "Every Cure 2025 Annual Report", "url": "https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf", "date": null, "written_by": "makers", "quote": "In January 2024, Joseph was on life support with POEMS syndrome, a rare blood disorder that caused his vital organs to shut down." }, { "kind": "report", "citation": "Advanced Research Projects Agency for Health. Fiscal Year 2027 Congressional Justification for Appropriations Committees, 17, “Repurposing for rare disease.”", "title": "Fiscal Year 2027 Congressional Justification for Appropriations Committees", "url": "https://arpa-h.gov/sites/default/files/2026-04/FY27%20ARPA-H%20CJ_Greenlight_508%20compliant.pdf", "date": null, "written_by": "unknown", "quote": null }, { "kind": "other", "citation": "Penn Medicine. “Finding Hidden Cures | Dr. David Fajgenbaum & Joseph’s Story.” Video, 14:19, November 17, 2025, 8:26–9:04 and 9:52–11:25. Publisher-supplied English captions.", "title": "Finding Hidden Cures | Dr. David Fajgenbaum & Joseph's Story", "url": "https://www.youtube.com/watch?v=4FxwoOuPGWs", "date": "2025-11-17", "written_by": "makers", "quote": "this AI algorithm that we use also scored those three drugs highly." }, { "kind": "news report", "citation": "Stacy Weiner. “This doctor saved his own life. Now he’s on a mission to save thousands more.” AAMCNews, September 24, 2024, response to “Has Every Cure had any successes yet?”", "title": "This doctor saved his own life. Now he’s on a mission to save thousands more", "url": "https://www.aamc.org/news/doctor-saved-his-own-life-now-he-s-mission-save-thousands-more", "date": "2024-09-24", "written_by": "deployer", "quote": null }, { "kind": "other", "citation": "David C. Fajgenbaum, Sally Nijim, Grant Mitchell, Matej Macak, Chris Bizon, Alexander Tropsha, and David Koslicki. “Pioneering a new field of computational pharmacophenomics to unlock the life-saving potential of existing medicines.” The Lancet Haematology 12, no. 2 (February 2025): e94–e96. Commentary, paragraph beginning “We have already begun to pilot these processes.” https://doi.org/10.1016/S2352-3026(24)00278-3.", "title": "Pioneering a new field of computational pharmacophenomics to unlock the life-saving potential of existing medicines", "url": "https://doi.org/10.1016/S2352-3026(24)00278-3", "date": null, "written_by": "makers", "quote": null }, { "kind": "news report", "citation": "Liz Tung. “UPenn professor receives $48.3 million to find new treatments in old drugs.” WHYY, March 10, 2024, opening POEMS account and “Harnessing the power of AI.”", "title": "UPenn professor receives $48.3 million to find new treatments in old drugs", "url": "https://whyy.org/articles/ai-platform-every-cure-medicine-disease-treatment-university-pennyslvania/", "date": "2024-03-10", "written_by": "independent", "quote": null }, { "kind": "news report", "citation": "Ann-Marie Roche. “Elsevier and Every Cure: treating rare diseases with generic drugs — at scale.” Elsevier Connect, January 30, 2024.", "title": "Elsevier and Every Cure: treating rare diseases with generic drugs — at scale", "url": "https://www.elsevier.com/en-gb/connect/elsevier-and-every-cure-treating-rare-diseases-with-generic-drugs-at-scale", "date": "2024-01-30", "written_by": "makers", "quote": null } ], "replication": { "produced_by": [ "Fajgenbaum recognized similarities between POEMS syndrome and multiple myeloma and reviewed high AI scores for drugs that were used for myeloma.", "Fajgenbaum answered the family’s urgent appeal and discussed treatment with Wayne Gao, who assessed the risks and administered the three drugs." ], "must_hold": [ "Clinicians must assess the proposed drugs, the patient’s condition, and the risks of treatment. A high model score alone does not establish that a drug is suitable.", "The patient must respond sufficiently to receive any further treatment that is needed. Coates later underwent a stem cell transplant before he reported full remission." ], "echoes": [] }, "paired_incident": null, "headline": "A man with a rare blood disorder became well enough for a transplant", "metric": "he responded within one or two weeks", "comparator": { "against": "the treatments his doctors had tried, with hospice as the remaining option", "before": "Coates was now entering a terminal stage: his heart and kidneys were failing, and fluid had to be drained from his belly several times a week. He was too sick to undergo a stem-cell transplant, which could save his life.", "after": "within days Coates started to improve. A few months later, he'd recovered sufficiently to receive a stem-cell transplant. He is now in remission.", "basis": "measured", "quote": "But, with little to lose, they gave it a try—and within days Coates started to improve. A few months later, he'd recovered sufficiently to receive a stem-cell transplant. He is now in remission.", "url": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have" }, "later": { "status": "persisted", "date": null, "note": "Every Cure’s 2025 annual report states that Joseph remains in remission. Its patient story is on page 15. The New Yorker also reported remission in July 2025. In Penn Medicine’s documentary, published on November 17, 2025, Coates says that full remission followed five months after his transplant. The annual report’s exact publication day is not established here.", "quote": "Within a week, Joseph began improving. Four months later, he was healthy enough to receive a stem cell transplant. Today, he remains in remission — and makes the most of what he and Dr. Fajgenbaum call \"overtime.\"", "url": "https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf" }, "value": null, "developer_country": "United States", "deployer_country": null, "unrated_because": null, "brief_notes": null, "brief": null, "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the OECD Monitor entry and the cited sources.", "source": "https://oecd.ai/en/incidents/2025-03-21-aa9f", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against, what happened since, the model version from the cited sources.", "source": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have; https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf; https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Improved Physical Health under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.", "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer added from the organization's own site or a registry.", "source": "https://everycure.org/privacy-policy/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: a rating reason, account, purpose, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "source": null, "editor": "AIBD" }, { "date": "2026-10-23", "change": "Personal benefit depth changed from 4 to 5 for the reported life-preserving outcome.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Consolidated the NYT original and its licensed Spanish edition as one reporting origin. Retained the New Yorker for its separate interview and named regimen, Every Cure's portfolio for the algorithm and treatment date, and its annual report for follow-up. Corrected the annual-report locator to printed page 15. Removed the redundant TED retelling and unsupported precision in the annual-report follow-up date.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Reworded the headline to identify the AI contribution as proposing the drug regimen. The account retains the subsequent improvement, stem cell transplant, and remission.", "source": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Rewrote the short title and summary in plain language, preserving the reported benefit and material limits. Added the named publication or institution to the reviewed lead source for homepage display.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Identified the AI system or feature in the supporting summary, or stated that the source does not name the software. Preserved the reported benefit and material qualifications.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Traced the system identity beyond the original case report. Added product names and supporting original sources, preserving historical-version limits and any inference in the source notes.", "source": "https://arpa-h.gov/sites/default/files/2026-04/FY27%20ARPA-H%20CJ_Greenlight_508%20compliant.pdf", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Shortened the homepage supporting statement to one sentence naming the system and its contribution; retained detailed outcomes and qualifications in the case account and source notes.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Revised the title and subtitle for natural phrasing, with named researchers, shorter dependencies, and less compressed terminology; preserved the system identities and evidence qualifications.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Placed the beneficiary’s personal name in the subtitle and kept the display headline focused on the reported benefit.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Described the intermediary by his role in the subtitle while retaining his full name and affiliation in the complete record.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Read the original English New York Times article through its archived copy, including the treating physician's interview and embedded research links. Named Wayne Gao as the treating physician. Resolved the English-text access limitation and recorded that the linked medical paper concerns a different patient. The archive remains an access copy of the existing source.", "source": "https://archive.ph/5xNut", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Added original patient and physician interviews, an early WHYY account, and the investigators’ Lancet Haematology commentary. Clarified that physicians considered and selected drugs that AI also scored highly. Distinguished the initial response from remission after transplantation, preserved uncertainty about the exact model, and recorded clinical precedents involving other patients. Added Penn Medicine beside the NYT source on the homepage.", "source": "https://www.youtube.com/watch?v=4FxwoOuPGWs", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Replaced the later platform name with a descriptive name for the early Every Cure system. Added contemporary evidence of multiple algorithms and recorded that the exact model, provider, and release for Coates’s scores remain unreported.", "source": "https://www.elsevier.com/en-gb/connect/elsevier-and-every-cure-treating-rare-diseases-with-generic-drugs-at-scale", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Revised the homepage subtitle for concise database prose, with courtesy titles for named beneficiaries and numbered clauses for the Coates drug-selection account. Preserved the reported evidence and material uncertainty.", "source": null, "editor": "AIBD" } ], "confidence": "reported", "shade": "medium", "claim_status": "Independently reported", "claim_basis": "Sources: three independent news reports, the makers' report, the makers' news report, the makers' press release, two other sources from the makers, the deployer's news report and one report with authorship relationship unassessed. The cited evidence includes no independent study or report and no finding by a regulator or court.", "profile": { "case_id": "AIBD-0127", "catalog_version": "1.0.0", "source_fingerprint": "fe0be1b2a61438f2745378b83c663e369f6a01d69068c3e40452180265ca4413", "collection_refs": [ { "collection_id": "aibd", "version": "snapshot-8bf7cfec9cb185aa" }, { "collection_id": "aibd", "version": "2026-10-25" } ], "source_ids": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "families": { "strategic assessments": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "evaluations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "monetary observations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "institutional decisions": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] } }, "fields": { "actors[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "developer": "Every Cure (co-founded by David Fajgenbaum, University of Pennsylvania)", "deployer": "David Fajgenbaum (Every Cure / University of Pennsylvania); regimen administered by Wayne Gao, Coates's treating hematologist and oncologist" } }, "provenance": { "kind": "legacy_record", "basis": "Updated the fields affected by the original English article review.", "record_fields": [ "developer", "deployer" ], "source_refs": [], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "actors[].ownership_control": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "ai_contribution": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ai_role": { "status": "assessed", "statement": "Fajgenbaum said that he had considered three drugs used for multiple myeloma and that Every Cure’s AI algorithm also scored them highly for POEMS syndrome. In an earlier AAMC interview, he described reviewing the scores and recommending the drugs to Coates’s treating physician. Wayne Gao weighed the risks and administered the treatment. The AI therefore supported the physicians’ assessment of candidate drugs. The sources do not show that it independently devised the regimen or that the benefit would have been impossible without it. The Lancet Haematology commentary contains a brief vignette of a matching unnamed POEMS patient, explicitly labeled unpublished data. No detailed clinical case report, underlying medical records, or case-specific model output was located. The commentary names KGML-xDTD as one of several algorithms in Every Cure’s platform, but it does not establish which algorithm or release was used for Coates." } } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "ai_role" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial", "display": { "answer": "A consulting physician considered three myeloma drugs and reviewed the high scores that Every Cure’s algorithm gave them for POEMS syndrome. The treating physician assessed the risks and administered them. The available accounts do not isolate the AI’s contribution to recovery.", "editor_note": "" } }, "ai_relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "category": "benefit created", "ai_role": { "status": "assessed", "statement": "Fajgenbaum said that he had considered three drugs used for multiple myeloma and that Every Cure’s AI algorithm also scored them highly for POEMS syndrome. In an earlier AAMC interview, he described reviewing the scores and recommending the drugs to Coates’s treating physician. Wayne Gao weighed the risks and administered the treatment. The AI therefore supported the physicians’ assessment of candidate drugs. The sources do not show that it independently devised the regimen or that the benefit would have been impossible without it. The Lancet Haematology commentary contains a brief vignette of a matching unnamed POEMS patient, explicitly labeled unpublished data. No detailed clinical case report, underlying medical records, or case-specific model output was located. The commentary names KGML-xDTD as one of several algorithms in Every Cure’s platform, but it does not establish which algorithm or release was used for Coates." } } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "category", "ai_role" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "assessments[].alternatives": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].assessor_date": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].depth": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "depth": 5, "reason": "Coates was critically ill, too sick for a transplant, and facing hospice care. He reported that he began responding to the drug regimen within one or two weeks, later received a stem cell transplant, and reached full remission five months after that transplant. The reported benefit was life-preserving. The available evidence does not isolate AI’s contribution from clinical judgment, the drugs, supportive care, or the transplant." } ] } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "ratings" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "assessments[].display_confidence": { "state": "value_present", "value": { "kind": "structured", "data": { "confidence": "medium", "evidence_word": "reported", "claim_status": "Independently reported", "basis": "Original interviews and institutional accounts support the reported treatment and recovery. The investigators’ commentary contains a brief vignette labeled unpublished data. Elsevier’s interview adds technical context. No detailed clinical case report or independent evaluation of AI’s contribution was located.", "interpretation": "The display rule remains unchanged. Originality and independence are assessed by claim in the source lineage. Several accounts share Fajgenbaum’s testimony. Neither the institutional documentary nor the investigators’ commentary establishes independent clinical confirmation, and the separate clinical precedents do not contribute to this case’s confidence.", "system_identity_review": "Additional sources clarify technical identity or chronology. They do not establish the AI contribution independently of the original investigators or witnesses." } }, "provenance": { "kind": "source_review", "basis": "Recomputed the existing display rule after adding the reviewed sources. Confidence remains medium; contextual evidence involving other patients is excluded from the calculation.", "record_fields": [ "evidence" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "assessments[].rationale": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "depth": 5, "reason": "Coates was critically ill, too sick for a transplant, and facing hospice care. He reported that he began responding to the drug regimen within one or two weeks, later received a stem cell transplant, and reached full remission five months after that transplant. The reported benefit was life-preserving. The available evidence does not isolate AI’s contribution from clinical judgment, the drugs, supportive care, or the transplant." } ] } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "ratings" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial", "display": { "answer": "Coates was critically ill and too sick for a transplant. He reported that he responded to the drugs within one or two weeks, later received a transplant, and reached remission five months afterward. The benefit was life-preserving, with the contribution from AI inseparable from the rest of his care.", "editor_note": "" } }, "assessments[].rubric_version": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].status_basis": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].target": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "depth": 5, "reason": "Coates was critically ill, too sick for a transplant, and facing hospice care. He reported that he began responding to the drug regimen within one or two weeks, later received a stem cell transplant, and reached full remission five months after that transplant. The reported benefit was life-preserving. The available evidence does not isolate AI’s contribution from clinical judgment, the drugs, supportive care, or the transplant." } ] } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "ratings" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "availability": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "brief": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "case_kind": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "case_links[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].evidence_links": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].evidence_strength": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].missingness": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].proposition": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "cross_border_flows[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "decisions[].action_outcome": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].grounds": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].institution_task": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].success_criterion": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "deployment_stage": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "economics[].amount": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].costs[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].counterfactual": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].currency_price_basis": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].gross_net": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].measure_type": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].period_unit": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].realization": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].recipient_payer": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].return_payback": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].valuation_method": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "evaluations[].ai_uplift": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].comparator": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].design": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].effect": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].exposure": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].id": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].measurement_method": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].metric": { "state": "not_assessed", "provenance": { "kind": "legacy_record", "basis": "Mapped from the existing case description without a new external source review.", "record_fields": [ "metric" ], "source_refs": [] }, "review_state": "not_assessed", "coverage": "partial", "family": "evaluations", "display": { "answer": "he responded within one or two weeks", "editor_note": "" } }, "evaluations[].reproduction_materials": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].setting_sample": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].uncertainty_limitations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "external_references[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "registry_ids": { "oecd_aim": "2025-03-21-aa9f" } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "registry_ids" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "follow_up[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "later": { "status": "persisted", "note": "Every Cure’s 2025 annual report states that Joseph remains in remission. Its patient story is on page 15. The New Yorker also reported remission in July 2025. In Penn Medicine’s documentary, published on November 17, 2025, Coates says that full remission followed five months after his transplant. The annual report’s exact publication day is not established here.", "quote": "Within a week, Joseph began improving. Four months later, he was healthy enough to receive a stem cell transplant. Today, he remains in remission — and makes the most of what he and Dr. Fajgenbaum call \"overtime.\"", "url": "https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf" } } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "later" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial", "display": { "answer": "Every Cure’s 2025 annual report states that Coates remains in remission. In Penn Medicine’s November 2025 documentary, he says that full remission followed five months after his transplant.", "editor_note": "" } }, "human_oversight": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "id": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "id": "AIBD-0127" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "id" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "infrastructure_dependencies[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].beneficiaries": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].beneficiary_count": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].benefit_type": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "benefit_type": "Improved Physical Health" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "benefit_type" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].claim": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "In January 2024, Joseph Coates, 37, of Renton, Washington, was critically ill with POEMS syndrome. His heart and kidneys were failing, and he was too sick for a stem cell transplant. His partner, Tara Theobald, asked David Fajgenbaum of the University of Pennsylvania and Every Cure for help. Fajgenbaum considered three drugs used for multiple myeloma, a related disease. He later explained that an early Every Cure algorithm also scored those drugs highly for POEMS. He recommended carfilzomib, cyclophosphamide, and dexamethasone to Coates’s treating hematologist and oncologist, Wayne Gao, who agreed to administer them. Coates later reported that he responded within one or two weeks and left intensive care three weeks later. He recovered enough to receive a stem cell transplant and reported full remission five months after that transplant. The New York Times reported improvement within a week and transplant eligibility about four months later. A brief vignette in The Lancet Haematology describes a matching unnamed patient and labels the result unpublished data. The sources support a contribution from AI alongside the physicians’ judgment, but they do not establish the exact model release or isolate its effect on recovery.", "benefit_type": "Improved Physical Health" } }, "provenance": { "kind": "source_review", "basis": "Updated the mapped values after reviewing system identity and distinguishing product, hardware, and model versions.", "record_fields": [ "account", "benefit_type" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial", "display": { "answer": "Coates reported that he responded to treatment within one or two weeks and later became well enough for a stem cell transplant.", "editor_note": "" } }, "outcomes[].distribution": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].duration": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].id": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].stakeholder_group": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "depth": 5, "reason": "Coates was critically ill, too sick for a transplant, and facing hospice care. He reported that he began responding to the drug regimen within one or two weeks, later received a stem cell transplant, and reached full remission five months after that transplant. The reported benefit was life-preserving. The available evidence does not isolate AI’s contribution from clinical judgment, the drugs, supportive care, or the transplant." } ] } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "ratings" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "outcomes[].status": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].tradeoffs": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].unexpected": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "unexpected": false, "purpose": "Every Cure uses AI to rank existing drugs as candidates for other diseases. Its early algorithms helped Fajgenbaum assess drugs that he had considered for Coates’s POEMS syndrome. The New Yorker notes that Every Cure does not usually make recommendations for individual patients." } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "unexpected", "purpose" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "places[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "location": "Renton, United States", "developer_country": "United States" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "location", "developer_country" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "purpose": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "purpose": "Every Cure uses AI to rank existing drugs as candidates for other diseases. Its early algorithms helped Fajgenbaum assess drugs that he had considered for Coates’s POEMS syndrome. The New Yorker notes that Every Cure does not usually make recommendations for individual patients." } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "purpose" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial", "display": { "answer": "Every Cure ranks existing drugs for potential use against other diseases. Its early system helped a physician assess drugs that he had considered for Coates.", "editor_note": "" } }, "record_dates": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "date_observed": "2025-03-20", "date_basis": "source publication", "date_precision": "day", "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the OECD Monitor entry and the cited sources.", "source": "https://oecd.ai/en/incidents/2025-03-21-aa9f", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against, what happened since, the model version from the cited sources.", "source": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have; https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf; https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Improved Physical Health under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.", "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer added from the organization's own site or a registry.", "source": "https://everycure.org/privacy-policy/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: a rating reason, account, purpose, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-23", "change": "Personal benefit depth changed from 4 to 5 for the reported life-preserving outcome.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Consolidated the NYT original and its licensed Spanish edition as one reporting origin. Retained the New Yorker for its separate interview and named regimen, Every Cure's portfolio for the algorithm and treatment date, and its annual report for follow-up. Corrected the annual-report locator to printed page 15. Removed the redundant TED retelling and unsupported precision in the annual-report follow-up date.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Reworded the headline to identify the AI contribution as proposing the drug regimen. The account retains the subsequent improvement, stem cell transplant, and remission.", "source": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Rewrote the short title and summary in plain language, preserving the reported benefit and material limits. Added the named publication or institution to the reviewed lead source for homepage display.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Identified the AI system or feature in the supporting summary, or stated that the source does not name the software. Preserved the reported benefit and material qualifications.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Traced the system identity beyond the original case report. Added product names and supporting original sources, preserving historical-version limits and any inference in the source notes.", "source": "https://arpa-h.gov/sites/default/files/2026-04/FY27%20ARPA-H%20CJ_Greenlight_508%20compliant.pdf", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Shortened the homepage supporting statement to one sentence naming the system and its contribution; retained detailed outcomes and qualifications in the case account and source notes.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Revised the title and subtitle for natural phrasing, with named researchers, shorter dependencies, and less compressed terminology; preserved the system identities and evidence qualifications.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Placed the beneficiary’s personal name in the subtitle and kept the display headline focused on the reported benefit.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Described the intermediary by his role in the subtitle while retaining his full name and affiliation in the complete record.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Read the original English New York Times article through its archived copy, including the treating physician's interview and embedded research links. Named Wayne Gao as the treating physician. Resolved the English-text access limitation and recorded that the linked medical paper concerns a different patient. The archive remains an access copy of the existing source.", "source": "https://archive.ph/5xNut", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Added original patient and physician interviews, an early WHYY account, and the investigators’ Lancet Haematology commentary. Clarified that physicians considered and selected drugs that AI also scored highly. Distinguished the initial response from remission after transplantation, preserved uncertainty about the exact model, and recorded clinical precedents involving other patients. Added Penn Medicine beside the NYT source on the homepage.", "source": "https://www.youtube.com/watch?v=4FxwoOuPGWs", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Replaced the later platform name with a descriptive name for the early Every Cure system. Added contemporary evidence of multiple algorithms and recorded that the exact model, provider, and release for Coates’s scores remain unreported.", "source": "https://www.elsevier.com/en-gb/connect/elsevier-and-every-cure-treating-rare-diseases-with-generic-drugs-at-scale", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Revised the homepage subtitle for concise database prose, with courtesy titles for named beneficiaries and numbered clauses for the Coates drug-selection account. Preserved the reported evidence and material uncertainty.", "editor": "AIBD" } ] } }, "provenance": { "kind": "curatorial", "basis": "Updated the displayed wording and revision history without changing the reviewed facts, sources, or assessments.", "record_fields": [ "date_observed", "revisions", "date_basis", "date_precision" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "replication.attempts[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "replication.conditions": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "replication": { "produced_by": [ "Fajgenbaum recognized similarities between POEMS syndrome and multiple myeloma and reviewed high AI scores for drugs that were used for myeloma.", "Fajgenbaum answered the family’s urgent appeal and discussed treatment with Wayne Gao, who assessed the risks and administered the three drugs." ], "must_hold": [ "Clinicians must assess the proposed drugs, the patient’s condition, and the risks of treatment. A high model score alone does not establish that a drug is suitable.", "The patient must respond sufficiently to receive any further treatment that is needed. Coates later underwent a stem cell transplant before he reported full remission." ], "echoes": [] } } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "replication" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial", "display": { "answer": "Clinicians need to assess the patient’s condition, the drugs, and their risks. A high AI score does not establish suitability. In this instance, recovery also depended on a response sufficient to permit a later transplant.", "editor_note": "" } }, "revision_history[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the OECD Monitor entry and the cited sources.", "source": "https://oecd.ai/en/incidents/2025-03-21-aa9f", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against, what happened since, the model version from the cited sources.", "source": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have; https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf; https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Improved Physical Health under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.", "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer added from the organization's own site or a registry.", "source": "https://everycure.org/privacy-policy/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: a rating reason, account, purpose, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-23", "change": "Personal benefit depth changed from 4 to 5 for the reported life-preserving outcome.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Consolidated the NYT original and its licensed Spanish edition as one reporting origin. Retained the New Yorker for its separate interview and named regimen, Every Cure's portfolio for the algorithm and treatment date, and its annual report for follow-up. Corrected the annual-report locator to printed page 15. Removed the redundant TED retelling and unsupported precision in the annual-report follow-up date.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Reworded the headline to identify the AI contribution as proposing the drug regimen. The account retains the subsequent improvement, stem cell transplant, and remission.", "source": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Rewrote the short title and summary in plain language, preserving the reported benefit and material limits. Added the named publication or institution to the reviewed lead source for homepage display.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Identified the AI system or feature in the supporting summary, or stated that the source does not name the software. Preserved the reported benefit and material qualifications.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Traced the system identity beyond the original case report. Added product names and supporting original sources, preserving historical-version limits and any inference in the source notes.", "source": "https://arpa-h.gov/sites/default/files/2026-04/FY27%20ARPA-H%20CJ_Greenlight_508%20compliant.pdf", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Shortened the homepage supporting statement to one sentence naming the system and its contribution; retained detailed outcomes and qualifications in the case account and source notes.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Revised the title and subtitle for natural phrasing, with named researchers, shorter dependencies, and less compressed terminology; preserved the system identities and evidence qualifications.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Placed the beneficiary’s personal name in the subtitle and kept the display headline focused on the reported benefit.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Described the intermediary by his role in the subtitle while retaining his full name and affiliation in the complete record.", "source": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Read the original English New York Times article through its archived copy, including the treating physician's interview and embedded research links. Named Wayne Gao as the treating physician. Resolved the English-text access limitation and recorded that the linked medical paper concerns a different patient. The archive remains an access copy of the existing source.", "source": "https://archive.ph/5xNut", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Added original patient and physician interviews, an early WHYY account, and the investigators’ Lancet Haematology commentary. Clarified that physicians considered and selected drugs that AI also scored highly. Distinguished the initial response from remission after transplantation, preserved uncertainty about the exact model, and recorded clinical precedents involving other patients. Added Penn Medicine beside the NYT source on the homepage.", "source": "https://www.youtube.com/watch?v=4FxwoOuPGWs", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Replaced the later platform name with a descriptive name for the early Every Cure system. Added contemporary evidence of multiple algorithms and recorded that the exact model, provider, and release for Coates’s scores remain unreported.", "source": "https://www.elsevier.com/en-gb/connect/elsevier-and-every-cure-treating-rare-diseases-with-generic-drugs-at-scale", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Revised the homepage subtitle for concise database prose, with courtesy titles for named beneficiaries and numbered clauses for the Coates drug-selection account. Preserved the reported evidence and material uncertainty.", "editor": "AIBD" } ] } }, "provenance": { "kind": "curatorial", "basis": "Updated the displayed wording and revision history without changing the reviewed facts, sources, or assessments.", "record_fields": [ "revisions" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "sector": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "domain": "Healthcare - rare disease / drug repurposing", "segment": "Individual off-label treatment of a terminal POEMS syndrome patient" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "domain", "segment" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].access_version": { "state": "value_present", "value": { "kind": "structured", "data": { "reviewed_on": "2026-10-24", "versions_and_access": [ { "source_url": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "access_url": "https://archive.ph/5xNut", "accessed_on": "2026-10-24", "capture_timestamp": "2026-09-24T11:14:37Z", "publication_date": "2025-03-20", "status": "Complete original English article and embedded links inspected in the archived copy. Includes interviews with Coates, Fajgenbaum, and treating physician Wayne Gao. The capture date does not replace the original publication date." }, { "source_url": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "access_url": "https://www.infobae.com/america/the-new-york-times/2025/03/24/los-medicos-le-dijeron-que-iba-a-morir-pero-la-inteligencia-artificial-le-salvo-la-vida/", "accessed_on": "2026-10-24", "status": "Licensed full-text Spanish translation inspected as an alternate access copy of the same article." }, { "source_url": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "status": "Publisher page inspected through its embedded full article text." }, { "source_url": "https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf", "locator": "Printed page 15, also the fifteenth page in the downloaded file.", "publication_date": "Exact day not established." }, { "source_url": "https://arpa-h.gov/sites/default/files/2026-04/FY27%20ARPA-H%20CJ_Greenlight_508%20compliant.pdf", "status": "Original source inspected.", "locator": "Printed p. 17, Repurposing for rare disease.", "reviewed_on": "2026-10-24" }, { "source_url": "https://everycure.org/portfolio/", "status": "POEMS entry and its link to the original NYT story are accessible and were reread.", "locator": "Carfilzomib-cyclophosphamide-dexamethasone for POEMS syndrome.", "reviewed_on": "2026-10-24" }, { "source_url": "https://www.youtube.com/watch?v=4FxwoOuPGWs", "publication_date": "2025-11-17", "publication_precision": "day", "accessed_on": "2026-10-24", "status": "Complete documentary transcript inspected using the publisher-supplied English en-US captions. Official Penn Medicine video, 14:19. The manual caption track is distinct from the automatically generated captions.", "locator": "8:26–9:04 and 9:52–11:25." }, { "source_url": "https://www.aamc.org/news/doctor-saved-his-own-life-now-he-s-mission-save-thousands-more", "publication_date": "2024-09-24", "publication_precision": "day", "accessed_on": "2026-10-24", "status": "Original interview inspected on the AAMC publisher page. November 11, 2024 is the advertised conference appearance, not this article’s publication date.", "locator": "Response to “Has Every Cure had any successes yet?”" }, { "source_url": "https://doi.org/10.1016/S2352-3026(24)00278-3", "access_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12090018/", "publication_date": "2025-02", "publication_precision": "month", "accessed_on": "2026-10-24", "status": "Complete author manuscript inspected in PMC, including the vignette, platform description, references, and disclosures. Final journal pagination e94–e96. The PMC availability date is August 1, 2025 and is not the journal publication date. The evidence date is null because an exact publication day was not verified.", "locator": "Paragraph beginning “We have already begun to pilot these processes.”" }, { "source_url": "https://whyy.org/articles/ai-platform-every-cure-medicine-disease-treatment-university-pennyslvania/", "publication_date": "2024-03-10", "publication_precision": "day", "accessed_on": "2026-10-24", "status": "Original publisher article inspected. The embedded audio is another format of the same reporting, not a separate source.", "locator": "Opening POEMS account and “Harnessing the power of AI.”" }, { "source_url": "https://www.elsevier.com/en-gb/connect/elsevier-and-every-cure-treating-rare-diseases-with-generic-drugs-at-scale", "source_ref": "AIBD-0127-source-0010", "publication_date": "2024-01-30", "accessed_on": "2026-10-24", "status": "Original publisher text inspected.", "locator": "Opening description of the algorithms and responses about Elsevier’s contribution." } ], "limitations": [ "No detailed clinical case report, underlying medical records, drug doses, or case-specific model output for Coates was located. The Lancet commentary contains a brief unnamed vignette and explicitly labels the result unpublished data.", "The sources do not isolate AI’s contribution from the physicians’ judgment, the drug regimen, supportive care, and later transplantation. Coates places full remission five months after his transplant.", "MATRIX names the platform, but the precise algorithm and release used in January 2024 remain unknown. KGML-xDTD is one of several algorithms described later, not an established identification of the model used for Coates.", "The unnamed patients in WHYY, the Lancet commentary, and ARPA-H are matched to Coates by context. These identifications remain inferences. ARPA-H’s relative date differs from the January 2024 chronology.", "The NYT and Every Cure annual report say that improvement began within a week and that transplant eligibility followed about four months later. Coates recalls a response within one or two weeks in the documentary. The Lancet vignette gives nine months of remission at submission without a submission date or definition that reconciles it with Coates’s post-transplant timeline.", "The medical commentary, institutional film, and additional interviews share investigators or witnesses. Their publication in different outlets does not establish independent clinical confirmation." ] } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "evidence" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "complete", "display": { "answer": "Patient and physician interviews describe treatment and recovery. Detailed clinical records, drug doses, and the patient’s AI scores are unavailable. The accounts differ on the timing of treatment and recovery.", "editor_note": "The unnamed patients in the Lancet commentary, WHYY, and ARPA-H are matched to Coates by their disease, treatment, and circumstances (references 5, 8–9). ARPA-H gives a relative date that differs from Every Cure’s January 2024 chronology. The Lancet commentary labels its vignette unpublished data." } }, "sources[].citation_locator": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "evidence": [ { "kind": "news report", "citation": "Morgan, K. (2025). Doctors Told Him He Was Going to Die. Then A.I. Saved His Life. The New York Times, March 20, 2025.", "title": "Doctors Told Him He Was Going to Die. Then A.I. Saved His Life.", "url": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "date": "2025-03-20", "written_by": "independent" }, { "kind": "news report", "citation": "Khullar, D. (2025). Can A.I. Find Cures for Untreatable Diseases—Using Drugs We Already Have? The New Yorker, Open Questions, 15 July 2025.", "title": "Can A.I. Find Cures for Untreatable Diseases—Using Drugs We Already Have?", "url": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "date": "2025-07-15", "written_by": "independent", "quote": "used the organization's A.I. platform to recommend a combination of drugs normally used to treat a blood cancer: a steroid called dexamethasone; a chemotherapy called cyclophosphamide; an immunotherapy called carfilzomib." }, { "kind": "press release", "citation": "Every Cure. Repurposing Portfolio, “Carfilzomib-cyclophosphamide-dexamethasone for POEMS syndrome.”", "title": "Repurposing Portfolio", "url": "https://everycure.org/portfolio/", "written_by": "makers", "quote": "carfilzomib-cyclophosphamide-dexamethasone was administered to a POEMS patient in January 2024 who was getting ready to go onto hospice care, which ultimately saved his life" }, { "kind": "report", "citation": "Every Cure. 2025 Annual Report, “Joseph,” p. 15.", "title": "Every Cure 2025 Annual Report", "url": "https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf", "written_by": "makers", "quote": "In January 2024, Joseph was on life support with POEMS syndrome, a rare blood disorder that caused his vital organs to shut down." }, { "kind": "report", "citation": "Advanced Research Projects Agency for Health. Fiscal Year 2027 Congressional Justification for Appropriations Committees, 17, “Repurposing for rare disease.”", "title": "Fiscal Year 2027 Congressional Justification for Appropriations Committees", "url": "https://arpa-h.gov/sites/default/files/2026-04/FY27%20ARPA-H%20CJ_Greenlight_508%20compliant.pdf", "written_by": "unknown" }, { "kind": "other", "citation": "Penn Medicine. “Finding Hidden Cures | Dr. David Fajgenbaum & Joseph’s Story.” Video, 14:19, November 17, 2025, 8:26–9:04 and 9:52–11:25. Publisher-supplied English captions.", "title": "Finding Hidden Cures | Dr. David Fajgenbaum & Joseph's Story", "url": "https://www.youtube.com/watch?v=4FxwoOuPGWs", "date": "2025-11-17", "written_by": "makers", "quote": "this AI algorithm that we use also scored those three drugs highly." }, { "kind": "news report", "citation": "Stacy Weiner. “This doctor saved his own life. Now he’s on a mission to save thousands more.” AAMCNews, September 24, 2024, response to “Has Every Cure had any successes yet?”", "title": "This doctor saved his own life. Now he’s on a mission to save thousands more", "url": "https://www.aamc.org/news/doctor-saved-his-own-life-now-he-s-mission-save-thousands-more", "date": "2024-09-24", "written_by": "deployer" }, { "kind": "other", "citation": "David C. Fajgenbaum, Sally Nijim, Grant Mitchell, Matej Macak, Chris Bizon, Alexander Tropsha, and David Koslicki. “Pioneering a new field of computational pharmacophenomics to unlock the life-saving potential of existing medicines.” The Lancet Haematology 12, no. 2 (February 2025): e94–e96. Commentary, paragraph beginning “We have already begun to pilot these processes.” https://doi.org/10.1016/S2352-3026(24)00278-3.", "title": "Pioneering a new field of computational pharmacophenomics to unlock the life-saving potential of existing medicines", "url": "https://doi.org/10.1016/S2352-3026(24)00278-3", "written_by": "makers" }, { "kind": "news report", "citation": "Liz Tung. “UPenn professor receives $48.3 million to find new treatments in old drugs.” WHYY, March 10, 2024, opening POEMS account and “Harnessing the power of AI.”", "title": "UPenn professor receives $48.3 million to find new treatments in old drugs", "url": "https://whyy.org/articles/ai-platform-every-cure-medicine-disease-treatment-university-pennyslvania/", "date": "2024-03-10", "written_by": "independent" }, { "kind": "news report", "citation": "Ann-Marie Roche. “Elsevier and Every Cure: treating rare diseases with generic drugs — at scale.” Elsevier Connect, January 30, 2024.", "title": "Elsevier and Every Cure: treating rare diseases with generic drugs — at scale", "url": "https://www.elsevier.com/en-gb/connect/elsevier-and-every-cure-treating-rare-diseases-with-generic-drugs-at-scale", "date": "2024-01-30", "written_by": "makers" } ] } }, "provenance": { "kind": "source_review", "basis": "Updated the mapped values after reviewing system identity and distinguishing product, hardware, and model versions.", "record_fields": [ "evidence" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "sources[].id": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "role": "Retained evidence sources in reviewed order" }, "provenance": { "kind": "source_review", "basis": "Preserved existing source IDs and appended original sources that add technical detail or earlier testimony.", "record_fields": [ "evidence" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "complete" }, "sources[].language": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "sources[].relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "evidence": [ { "kind": "news report", "citation": "Morgan, K. (2025). Doctors Told Him He Was Going to Die. Then A.I. Saved His Life. The New York Times, March 20, 2025.", "title": "Doctors Told Him He Was Going to Die. Then A.I. Saved His Life.", "url": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "date": "2025-03-20", "written_by": "independent" }, { "kind": "news report", "citation": "Khullar, D. (2025). Can A.I. Find Cures for Untreatable Diseases—Using Drugs We Already Have? The New Yorker, Open Questions, 15 July 2025.", "title": "Can A.I. Find Cures for Untreatable Diseases—Using Drugs We Already Have?", "url": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "date": "2025-07-15", "written_by": "independent", "quote": "used the organization's A.I. platform to recommend a combination of drugs normally used to treat a blood cancer: a steroid called dexamethasone; a chemotherapy called cyclophosphamide; an immunotherapy called carfilzomib." }, { "kind": "press release", "citation": "Every Cure. Repurposing Portfolio, “Carfilzomib-cyclophosphamide-dexamethasone for POEMS syndrome.”", "title": "Repurposing Portfolio", "url": "https://everycure.org/portfolio/", "written_by": "makers", "quote": "carfilzomib-cyclophosphamide-dexamethasone was administered to a POEMS patient in January 2024 who was getting ready to go onto hospice care, which ultimately saved his life" }, { "kind": "report", "citation": "Every Cure. 2025 Annual Report, “Joseph,” p. 15.", "title": "Every Cure 2025 Annual Report", "url": "https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf", "written_by": "makers", "quote": "In January 2024, Joseph was on life support with POEMS syndrome, a rare blood disorder that caused his vital organs to shut down." }, { "kind": "report", "citation": "Advanced Research Projects Agency for Health. Fiscal Year 2027 Congressional Justification for Appropriations Committees, 17, “Repurposing for rare disease.”", "title": "Fiscal Year 2027 Congressional Justification for Appropriations Committees", "url": "https://arpa-h.gov/sites/default/files/2026-04/FY27%20ARPA-H%20CJ_Greenlight_508%20compliant.pdf", "written_by": "unknown" }, { "kind": "other", "citation": "Penn Medicine. “Finding Hidden Cures | Dr. David Fajgenbaum & Joseph’s Story.” Video, 14:19, November 17, 2025, 8:26–9:04 and 9:52–11:25. Publisher-supplied English captions.", "title": "Finding Hidden Cures | Dr. David Fajgenbaum & Joseph's Story", "url": "https://www.youtube.com/watch?v=4FxwoOuPGWs", "date": "2025-11-17", "written_by": "makers", "quote": "this AI algorithm that we use also scored those three drugs highly." }, { "kind": "news report", "citation": "Stacy Weiner. “This doctor saved his own life. Now he’s on a mission to save thousands more.” AAMCNews, September 24, 2024, response to “Has Every Cure had any successes yet?”", "title": "This doctor saved his own life. Now he’s on a mission to save thousands more", "url": "https://www.aamc.org/news/doctor-saved-his-own-life-now-he-s-mission-save-thousands-more", "date": "2024-09-24", "written_by": "deployer" }, { "kind": "other", "citation": "David C. Fajgenbaum, Sally Nijim, Grant Mitchell, Matej Macak, Chris Bizon, Alexander Tropsha, and David Koslicki. “Pioneering a new field of computational pharmacophenomics to unlock the life-saving potential of existing medicines.” The Lancet Haematology 12, no. 2 (February 2025): e94–e96. Commentary, paragraph beginning “We have already begun to pilot these processes.” https://doi.org/10.1016/S2352-3026(24)00278-3.", "title": "Pioneering a new field of computational pharmacophenomics to unlock the life-saving potential of existing medicines", "url": "https://doi.org/10.1016/S2352-3026(24)00278-3", "written_by": "makers" }, { "kind": "news report", "citation": "Liz Tung. “UPenn professor receives $48.3 million to find new treatments in old drugs.” WHYY, March 10, 2024, opening POEMS account and “Harnessing the power of AI.”", "title": "UPenn professor receives $48.3 million to find new treatments in old drugs", "url": "https://whyy.org/articles/ai-platform-every-cure-medicine-disease-treatment-university-pennyslvania/", "date": "2024-03-10", "written_by": "independent" }, { "kind": "news report", "citation": "Ann-Marie Roche. “Elsevier and Every Cure: treating rare diseases with generic drugs — at scale.” Elsevier Connect, January 30, 2024.", "title": "Elsevier and Every Cure: treating rare diseases with generic drugs — at scale", "url": "https://www.elsevier.com/en-gb/connect/elsevier-and-every-cure-treating-rare-diseases-with-generic-drugs-at-scale", "date": "2024-01-30", "written_by": "makers" } ] } }, "provenance": { "kind": "source_review", "basis": "Updated the mapped values after reviewing system identity and distinguishing product, hardware, and model versions.", "record_fields": [ "evidence" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "sources[].upstream_sources": { "state": "value_present", "value": { "kind": "structured", "data": { "reviewed_on": "2026-10-24", "lead_source_ref": "AIBD-0127-source-0001", "retained_source_order": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "origins": [ { "url": "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "contribution": "Original interviews with Coates, Fajgenbaum, and treating physician Wayne Gao support the reported condition, treatment decision, response within a week, later transplant, and remission.", "locator": "Opening patient narrative and final section, including the interview with treating physician Wayne Gao. Original English article read through the archived copy.", "relationship": "Original journalism with firsthand patient, treating physician, and researcher testimony. No medical records or clinical case report for Coates are supplied.", "source_refs": [ "AIBD-0127-source-0001" ], "display_name": "The New York Times", "access_url": "https://archive.ph/5xNut" }, { "url": "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "contribution": "Separate interview with Fajgenbaum identifies the three drugs and clinical decision.", "locator": "Paragraph beginning “Last year, Fajgenbaum received an e-mail”.", "relationship": "Independent reporter, same underlying case and researcher; not a new medical assessment.", "source_refs": [ "AIBD-0127-source-0002" ] }, { "url": "https://everycure.org/portfolio/", "contribution": "Developer specifies January 2024 and high algorithm scores alongside biological similarity.", "locator": "Carfilzomib-cyclophosphamide-dexamethasone for POEMS syndrome.", "relationship": "Developer account; its only case link returns to the NYT article.", "source_refs": [ "AIBD-0127-source-0003" ] }, { "url": "https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf", "contribution": "Later institutional account of remission.", "locator": "Printed p. 15, Joseph.", "relationship": "Every Cure account; patient testimony and developer report, not an independent clinical follow-up.", "source_refs": [ "AIBD-0127-source-0004" ] }, { "url": "https://arpa-h.gov/sites/default/files/2026-04/FY27%20ARPA-H%20CJ_Greenlight_508%20compliant.pdf", "contribution": "Names MATRIX and attributes a matching POEMS treatment to that toolkit.", "locator": "Printed p. 17, Repurposing for rare disease.", "relationship": "Funding agency’s retrospective account. The patient is unnamed and the relative date conflicts with the developer’s January 2024 chronology.", "source_refs": [ "AIBD-0127-source-0005" ], "display_name": "ARPA-H" }, { "url": "https://www.youtube.com/watch?v=4FxwoOuPGWs", "contribution": "Original interviews and patient videos explain how human judgment and AI scores contributed, give Coates’s response timeline, and place full remission after transplantation.", "locator": "6:44–8:16, failed prior treatment and hospice discussion; 8:26–9:04, knowledge graph, physician’s candidates, and AI scores; 9:52–10:00, response and transfer from CCU; 10:43–11:25, kidney recovery, transplantation, and later remission.", "relationship": "Produced by Penn Medicine, Fajgenbaum’s institution. Coates, Tara Theobald, and Fajgenbaum give firsthand testimony. Patient videos add contemporaneous testimony, but the film is not an independent clinical evaluation.", "source_refs": [ "AIBD-0127-source-0006" ], "display_name": "Penn Medicine" }, { "url": "https://www.aamc.org/news/doctor-saved-his-own-life-now-he-s-mission-save-thousands-more", "contribution": "An interview published in September 2024 names Joseph, dates the appeal to January, and describes reviewing AI scores before recommending three myeloma drugs to his doctor.", "locator": "Response to “Has Every Cure had any successes yet?” and preceding discussion of Every Cure’s platform.", "relationship": "Original interview conducted by Stacy Weiner for AAMCNews. The relevant answer is Fajgenbaum’s firsthand account as the recommending physician and platform cofounder, not independent clinical verification.", "source_refs": [ "AIBD-0127-source-0007" ], "display_name": "AAMC" }, { "url": "https://doi.org/10.1016/S2352-3026(24)00278-3", "access_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12090018/", "contribution": "The investigators describe reviewing platform scores for a refractory POEMS patient facing hospice and report nine months of remission at submission. They also describe the platform and identify KGML-xDTD as one of several algorithms.", "locator": "Paragraph beginning “We have already begun to pilot these processes”; platform description beginning “The Every Cure platform is built to integrate multiple knowledge sources”; reference 10.", "relationship": "Commentary by the platform’s investigators, with a brief clinical vignette explicitly labeled unpublished data. The patient is unnamed, so identification as Coates is inferred from the disease, hospice setting, drug class, and related firsthand accounts. It is not an independent study or a detailed clinical case report.", "source_refs": [ "AIBD-0127-source-0008" ], "display_name": "The Lancet Haematology", "publication_date": "2025-02", "publication_precision": "month" }, { "url": "https://whyy.org/articles/ai-platform-every-cure-medicine-disease-treatment-university-pennyslvania/", "contribution": "An early original interview reports that a Washington POEMS patient had left intensive care and the hospital after the three-drug recommendation. It also names MATRIX and describes the platform as being in beta in March 2024.", "locator": "Opening six paragraphs and “Harnessing the power of AI,” especially the paragraph beginning “Currently, Every Cure’s matchmaking program is in beta mode.”", "relationship": "Original reporting by Liz Tung. The clinical claims come from Fajgenbaum, and the patient is unnamed. Identification as Coates is inferred from Washington state, POEMS, the timing, the hospice plan, and the myeloma-drug recommendation. This is additional early testimony from the same physician, not independent clinical replication.", "source_refs": [ "AIBD-0127-source-0009" ], "display_name": "WHYY" }, { "url": "https://www.elsevier.com/en-gb/connect/elsevier-and-every-cure-treating-rare-diseases-with-generic-drugs-at-scale", "source_refs": [ "AIBD-0127-source-0010" ], "locator": "Opening description of the algorithms and responses about Elsevier’s contribution.", "display_name": "Elsevier", "contribution": "Contemporaneous interview establishes that Every Cure was using several algorithms, including customized Elsevier algorithms.", "relationship": "Technical partner’s interview with Fajgenbaum. It does not identify which algorithm supplied Coates’s scores or corroborate his clinical outcome." } ], "claim_chains": [ { "claim": "Treatment, response, and remission", "path": [ "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "https://archive.ph/5xNut", "https://www.infobae.com/america/the-new-york-times/2025/03/24/los-medicos-le-dijeron-que-iba-a-morir-pero-la-inteligencia-artificial-le-salvo-la-vida/", "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "https://everycure.org/wp-content/uploads/2026/01/EVery.Cure_.2025.Annual.Report.Single.Digital.Pages.pdf#page=15", "https://www.youtube.com/watch?v=4FxwoOuPGWs", "https://www.aamc.org/news/doctor-saved-his-own-life-now-he-s-mission-save-thousands-more", "https://doi.org/10.1016/S2352-3026(24)00278-3", "https://whyy.org/articles/ai-platform-every-cure-medicine-disease-treatment-university-pennyslvania/" ], "finding": "The NYT article, its archived English copy, and the licensed Infobae translation are one reporting origin. The original includes testimony from Coates and Wayne Gao. The New Yorker has its own interview. Penn Medicine adds original patient and partner testimony and earlier patient videos. AAMC and WHYY add earlier interviews with Fajgenbaum. The Lancet commentary gives a brief vignette labeled unpublished data. These sources are original accounts, but their shared witnesses and institutional relationships do not constitute independent clinical replication." }, { "claim": "AI recommendation and January 2024 chronology", "path": [ "https://everycure.org/portfolio/", "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "https://www.youtube.com/watch?v=4FxwoOuPGWs", "https://www.aamc.org/news/doctor-saved-his-own-life-now-he-s-mission-save-thousands-more", "https://whyy.org/articles/ai-platform-every-cure-medicine-disease-treatment-university-pennyslvania/", "https://doi.org/10.1016/S2352-3026(24)00278-3" ], "finding": "Fajgenbaum says in the documentary that he had considered the drugs and that AI also scored them highly. His September 2024 AAMC interview describes reviewing the scores before recommending drugs and explicitly dates Joseph’s crisis to January. WHYY’s March 2024 account describes a matching unnamed Washington patient about six weeks after the appeal. These accounts support AI-assisted assessment alongside clinical judgment, not the claim that AI alone invented an untested regimen." }, { "claim": "System identity", "path": [ "https://www.nytimes.com/2025/03/20/well/ai-drug-repurposing.html", "https://everycure.org/portfolio/", "https://www.newyorker.com/culture/open-questions/can-ai-find-cures-for-untreatable-diseases-using-drugs-we-already-have", "https://arpa-h.gov/sites/default/files/2026-04/FY27%20ARPA-H%20CJ_Greenlight_508%20compliant.pdf", "https://www.youtube.com/watch?v=4FxwoOuPGWs", "https://doi.org/10.1016/S2352-3026(24)00278-3", "https://whyy.org/articles/ai-platform-every-cure-medicine-disease-treatment-university-pennyslvania/", "https://www.elsevier.com/en-gb/connect/elsevier-and-every-cure-treating-rare-diseases-with-generic-drugs-at-scale" ], "finding": "Every Cure identifies an early version of its algorithms for the January 2024 treatment. A January 30 interview describes multiple algorithms, including Elsevier contributions, without identifying which produced Coates’s scores. WHYY names MATRIX in March 2024. Neither that platform name nor the later KGML-xDTD documentation establishes the algorithm or release used for Coates." }, { "claim": "Treatment novelty and the separate summer-2024 conference report", "path": [ "https://everycure.org/portfolio/", "https://doi.org/10.1016/j.jaccas.2020.12.027", "https://pmc.ncbi.nlm.nih.gov/articles/PMC8310984/", "https://library.ehaweb.org/eha/2024/eha2024-congress/document?c_id=421524&cm_id=436356&type=document436356" ], "finding": "A 2021 JACC case report describes the same three drugs for a different POEMS patient. EHA abstract PB2758 reports a separate eight-patient Qilu Hospital cohort, with seven responses. Neither source reports AI involvement. The EHA abstract is a plausible match for Every Cure’s uncited conference reference, but that match remains an inference. Both are clinical context, not evidence about Coates or independent verification of his AI-assisted recommendation." } ], "limitations": [ "No detailed clinical case report, underlying medical records, drug doses, or case-specific model output for Coates was located. The Lancet commentary contains a brief unnamed vignette and explicitly labels the result unpublished data.", "The sources do not isolate AI’s contribution from the physicians’ judgment, the drug regimen, supportive care, and later transplantation. Coates places full remission five months after his transplant.", "MATRIX names the platform, but the precise algorithm and release used in January 2024 remain unknown. KGML-xDTD is one of several algorithms described later, not an established identification of the model used for Coates.", "The unnamed patients in WHYY, the Lancet commentary, and ARPA-H are matched to Coates by context. These identifications remain inferences. ARPA-H’s relative date differs from the January 2024 chronology.", "The NYT and Every Cure annual report say that improvement began within a week and that transplant eligibility followed about four months later. Coates recalls a response within one or two weeks in the documentary. The Lancet vignette gives nine months of remission at submission without a submission date or definition that reconciles it with Coates’s post-transplant timeline.", "The medical commentary, institutional film, and additional interviews share investigators or witnesses. Their publication in different outlets does not establish independent clinical confirmation." ], "excluded_or_consolidated_sources": [ { "url": "https://www.infobae.com/america/the-new-york-times/2025/03/24/los-medicos-le-dijeron-que-iba-a-morir-pero-la-inteligencia-artificial-le-salvo-la-vida/", "reason": "Licensed translation of the NYT story, retained as an alternate access copy of the same reporting." }, { "url": "https://www.ted.com/talks/david_fajgenbaum_how_nearly_dying_helped_me_discover_my_own_cure_and_many_more/transcript", "reason": "Developer's TED retelling adds no necessary evidence beyond the portfolio, annual report, and original interviews." }, { "url": "https://archive.ph/5xNut", "reason": "Archived copy of the original English NYT article, captured on September 24, 2026, and inspected on October 24, 2026. The article was published on March 20, 2025. The copy is not a separate source or independent corroboration." } ], "review_scope": "Retained the archived English NYT review and added the complete Penn Medicine documentary and publisher captions, original AAMC and WHYY interviews, the Lancet Haematology author manuscript, and contextual clinical precedents. Distinguished original testimony from independent clinical confirmation and preserved uncertainty about patient matching, treatment timing, and the exact model. Reviewed the contemporary Elsevier interview and public MATRIX releases to distinguish the early system from subsequently documented implementations.", "embedded_reference_checks": [ { "url": "https://www.nejm.org/doi/full/10.1056/NEJMc2412494", "title": "Identifying and Targeting TNF Signaling in Idiopathic Multicentric Castleman’s Disease", "access_url": "https://pubmed.ncbi.nlm.nih.gov/39908436/", "finding": "The linked NEJM paper concerns an adalimumab-treated patient under Luke Chen’s care. Coates received carfilzomib, cyclophosphamide, and dexamethasone under Wayne Gao’s care. These are different patients and regimens, even though an earlier CDCN profile also described Coates as having POEMS-associated multicentric Castleman disease. The NEJM paper is not clinical documentation for Coates." }, { "url": "https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giad057/7246583", "title": "KGML-xDTD: a knowledge graph–based machine learning framework for drug treatment prediction and mechanism description", "finding": "The NYT links this methods paper as background. The Lancet Haematology commentary confirms that KGML-xDTD is one of several algorithms used in Every Cure’s platform. Neither paper establishes which algorithm or release contributed to Coates’s recommendation." }, { "url": "https://github.com/everycure-org/matrix/blob/25e1272fe14f4029627e91e1ad90a576e312ade4/docs/src/releases/posts/2024-11-27v0.2.5/post.md", "title": "MATRIX v0.2.5 release notes", "finding": "The November 28, 2024 notes describe KGML-xDTD and an integrated knowledge graph. The notes do not identify Coates’s earlier run. Public repository searches did not supply a case-specific configuration or checkpoint." } ], "homepage_source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0006" ], "earlier_reporting": [ { "url": "https://whyy.org/articles/ai-platform-every-cure-medicine-disease-treatment-university-pennyslvania/", "publication_date": "2024-03-10", "identification": "Patient unnamed; matching to Coates remains an inference." }, { "url": "https://www.aamc.org/news/doctor-saved-his-own-life-now-he-s-mission-save-thousands-more", "publication_date": "2024-09-24", "identification": "Names Joseph and January 2024; matching to Joseph Coates follows the surrounding case details." } ], "chronology_note": "The case date remains March 20, 2025, the NYT publication date recorded for this entry. Earlier reporting is preserved here without substituting a different date in this revision.", "contextual_clinical_precedents": [ { "url": "https://doi.org/10.1016/j.jaccas.2020.12.027", "access_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC8310984/", "title": "Pericardial Tamponade and Other Cardiac Complications in POEMS Syndrome", "citation": "Levene et al., JACC: Case Reports, 2021. https://doi.org/10.1016/j.jaccas.2020.12.027.", "locator": "Management and Follow-Up sections.", "finding": "A different 66-year-old patient treated at Oregon Health & Science University received carfilzomib, cyclophosphamide, and dexamethasone for POEMS syndrome. This establishes clinical use before Coates’s treatment. No AI contribution is described.", "relationship": "Contextual clinical precedent only. Not retained as evidence of Coates’s outcome and not counted toward confidence in this case." }, { "url": "https://library.ehaweb.org/eha/2024/eha2024-congress/document?c_id=421524&cm_id=436356&type=document436356", "title": "EFFICACY AND SAFETY OF CARFILZOMIB, CYCLOPHOSPHAMIDE AND DEXAMETHASONE FOR THE TREATMENT OF POEMS SYNDROME", "locator": "EHA 2024 abstract PB2758, Methods and Results. Publication-only abstract.", "publication_date": "2024", "publication_precision": "year", "access_note": "Full extracted text of the original EHA document was inspected. The individual abstract’s publication day and author list were not established. The congress abstract book was published on June 14, 2024, but that date is not substituted for the individual item’s unverified release date.", "finding": "A retrospective Qilu Hospital cohort included eight POEMS patients treated from March 2022 through January 2024. Seven responded, and one underwent autologous stem cell transplantation. These are other patients, and no AI involvement is stated.", "relationship": "Plausible match for Every Cure’s summer-2024 conference claim, but the portfolio does not cite PB2758, so the match remains inferential. Context only, not counted as evidence of Coates’s treatment or of AI’s benefit." } ], "diagnostic_history_note": { "url": "https://cdcn.org/wp-content/uploads/2023/12/CDCN-2023-Impact-Report.pdf", "locator": "November 2023 report, printed p. 4, “The Faces of Castleman Disease,” Joseph Coates.", "finding": "This earlier profile calls Coates’s condition POEMS-associated multicentric Castleman disease. That historical label does not make him the adalimumab-treated patient in the separate NEJM report." } } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "evidence", "system" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "complete", "display": { "answer": "Original interviews provide testimony from Coates and his physicians. Every Cure, Penn Medicine, and ARPA-H later describe the same treatment. The accounts share witnesses and investigators rather than providing independent clinical confirmation.", "editor_note": "" } }, "strategic_assessments[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "strategic assessments" }, "summary": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "summary": "Mr. Joseph Coates received three drugs (i) that a consulting physician had considered and (ii) that Every Cure’s early drug-repurposing system had scored highly.", "account": "In January 2024, Joseph Coates, 37, of Renton, Washington, was critically ill with POEMS syndrome. His heart and kidneys were failing, and he was too sick for a stem cell transplant. His partner, Tara Theobald, asked David Fajgenbaum of the University of Pennsylvania and Every Cure for help. Fajgenbaum considered three drugs used for multiple myeloma, a related disease. He later explained that an early Every Cure algorithm also scored those drugs highly for POEMS. He recommended carfilzomib, cyclophosphamide, and dexamethasone to Coates’s treating hematologist and oncologist, Wayne Gao, who agreed to administer them. Coates later reported that he responded within one or two weeks and left intensive care three weeks later. He recovered enough to receive a stem cell transplant and reported full remission five months after that transplant. The New York Times reported improvement within a week and transplant eligibility about four months later. A brief vignette in The Lancet Haematology describes a matching unnamed patient and labels the result unpublished data. The sources support a contribution from AI alongside the physicians’ judgment, but they do not establish the exact model release or isolate its effect on recovery." } }, "provenance": { "kind": "curatorial", "basis": "Updated the displayed wording and revision history without changing the reviewed facts, sources, or assessments.", "record_fields": [ "summary", "account" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "systems[].autonomy_permissions": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].component_role": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].deployment_configuration": { "state": "value_present", "value": { "kind": "structured", "data": { "use": "Drug-disease scoring to support the physicians’ assessment of candidate treatments for POEMS syndrome in January 2024.", "human_decision": "Fajgenbaum recommended the regimen; Wayne Gao weighed the risks and administered it.", "unreported_details": [ "Exact algorithm and release", "Input knowledge-graph snapshot", "Case-specific scores and run identifier" ], "historical_context": "MATRIX was publicly named by March 2024. Its subsequently published configuration is not a verified description of Coates’s January run." } }, "provenance": { "kind": "source_review", "basis": "Separated the reported clinical workflow from later platform documentation.", "record_fields": [ "system", "model_version" ], "source_refs": [ "AIBD-0127-source-0003", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial", "display": { "answer": "The system scored candidate drugs for POEMS syndrome in January 2024. Physicians reviewed the scores and chose the treatment.", "editor_note": "" } }, "systems[].inputs_outputs": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].model_name": { "state": "not_reported", "provenance": { "kind": "source_review", "basis": "The case accounts identify Every Cure’s early algorithms, but no reviewed source identifies the exact algorithm or model release that supplied Coates’s January 2024 scores. KGML-xDTD and the later documented MATRIX architecture cannot be assigned to this run.", "record_fields": [ "system", "model_version" ], "source_refs": [ "AIBD-0127-source-0003", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "reason": "The case accounts identify Every Cure’s early algorithms, but no reviewed source identifies the exact algorithm or model release that supplied Coates’s January 2024 scores. KGML-xDTD and the later documented MATRIX architecture cannot be assigned to this run.", "review_state": "reviewed", "coverage": "complete", "display": { "answer": "Every Cure’s early algorithm for scoring possible uses of drugs against diseases. The accounts do not identify which of its algorithms produced these scores.", "editor_note": "" } }, "systems[].model_version": { "state": "not_reported", "provenance": { "kind": "source_review", "basis": "The case accounts identify Every Cure’s early algorithms, but no reviewed source identifies the exact algorithm or model release that supplied Coates’s January 2024 scores. KGML-xDTD and the later documented MATRIX architecture cannot be assigned to this run.", "record_fields": [ "system", "model_version" ], "source_refs": [ "AIBD-0127-source-0003", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "reason": "The case accounts identify Every Cure’s early algorithms, but no reviewed source identifies the exact algorithm or model release that supplied Coates’s January 2024 scores. KGML-xDTD and the later documented MATRIX architecture cannot be assigned to this run.", "review_state": "reviewed", "coverage": "complete", "display": { "answer": "The January 2024 configuration has no published release identifier.", "editor_note": "" } }, "systems[].product_name": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "system": "Every Cure’s early drug-repurposing system" } }, "provenance": { "kind": "source_review", "basis": "Updated the mapped values after reviewing system identity and distinguishing product, hardware, and model versions.", "record_fields": [ "system" ], "source_refs": [ "AIBD-0127-source-0003", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "complete" }, "systems[].provider": { "state": "value_present", "value": { "kind": "structured", "data": { "application_developer": "Every Cure", "underlying_model_provider": "Not identified for this case." } }, "provenance": { "kind": "source_review", "basis": "Every Cure is identified in its own portfolio and Fajgenbaum’s accounts. The contemporary Elsevier interview establishes multiple contributing algorithms, without identifying the one used for Coates.", "record_fields": [ "developer", "system" ], "source_refs": [ "AIBD-0127-source-0003", "AIBD-0127-source-0006", "AIBD-0127-source-0010" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "taxonomy_crosswalks[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "title": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "title": "Physicians treated Joseph Coates’s POEMS syndrome with three drugs that an early Every Cure algorithm also ranked highly, allowing a later stem cell transplant and remission", "headline": "A man with a rare blood disorder became well enough for a transplant" } }, "provenance": { "kind": "source_review", "basis": "Reviewed original patient and physician accounts and the investigators’ commentary. Clarified AI’s contribution and separated unpublished clinical details, contextual precedents, and patient-matching inferences.", "record_fields": [ "title", "headline" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "version": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "fe0be1b2a61438f2745378b83c663e369f6a01d69068c3e40452180265ca4413" ], "role": "SHA-256 of normalized original case data" }, "provenance": { "kind": "curatorial", "basis": "Recomputed the fingerprint after the homepage copy revision.", "record_fields": [ "summary", "revisions" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "complete" }, "workflow": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "In January 2024, Joseph Coates, 37, of Renton, Washington, was critically ill with POEMS syndrome. His heart and kidneys were failing, and he was too sick for a stem cell transplant. His partner, Tara Theobald, asked David Fajgenbaum of the University of Pennsylvania and Every Cure for help. Fajgenbaum considered three drugs used for multiple myeloma, a related disease. He later explained that an early Every Cure algorithm also scored those drugs highly for POEMS. He recommended carfilzomib, cyclophosphamide, and dexamethasone to Coates’s treating hematologist and oncologist, Wayne Gao, who agreed to administer them. Coates later reported that he responded within one or two weeks and left intensive care three weeks later. He recovered enough to receive a stem cell transplant and reported full remission five months after that transplant. The New York Times reported improvement within a week and transplant eligibility about four months later. A brief vignette in The Lancet Haematology describes a matching unnamed patient and labels the result unpublished data. The sources support a contribution from AI alongside the physicians’ judgment, but they do not establish the exact model release or isolate its effect on recovery.", "replication": { "produced_by": [ "Fajgenbaum recognized similarities between POEMS syndrome and multiple myeloma and reviewed high AI scores for drugs that were used for myeloma.", "Fajgenbaum answered the family’s urgent appeal and discussed treatment with Wayne Gao, who assessed the risks and administered the three drugs." ], "must_hold": [ "Clinicians must assess the proposed drugs, the patient’s condition, and the risks of treatment. A high model score alone does not establish that a drug is suitable.", "The patient must respond sufficiently to receive any further treatment that is needed. Coates later underwent a stem cell transplant before he reported full remission." ], "echoes": [] } } }, "provenance": { "kind": "source_review", "basis": "Updated the mapped values after reviewing system identity and distinguishing product, hardware, and model versions.", "record_fields": [ "account", "replication" ], "source_refs": [ "AIBD-0127-source-0001", "AIBD-0127-source-0002", "AIBD-0127-source-0003", "AIBD-0127-source-0004", "AIBD-0127-source-0005", "AIBD-0127-source-0006", "AIBD-0127-source-0007", "AIBD-0127-source-0008", "AIBD-0127-source-0009" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial", "display": { "answer": "The consulting physician recognized similarities between POEMS syndrome and multiple myeloma and reviewed the AI scores for drugs that were used for myeloma. He discussed treatment with the physician responsible for Coates, who assessed the risks and administered the drugs.", "editor_note": "" } } }, "summary": { "total": 91, "addressed": 91, "known": 32, "reviewed": 27, "record_mapped": 7, "not_assessed": 57, "complete": false, "by_state": { "value_present": 32, "not_reported": 2, "unresolved": 0, "not_assessed": 57, "not_applicable": 0, "withheld": 0, "source_unavailable": 0 } } } }