{ "id": "AIBD-0311", "title": "Cerebral's CMD-1 NLP crisis-message detector cuts median time to crisis-specialist triage from about 9 hours to 8–13 minutes in a prospective October 2022 deployment", "summary": "Two-stage NLP (keyword filter plus logistic regression) screened 102,471 chat messages in October 2022 (AUC 0.98, sensitivity 0.98); daily median receipt-to-triage time 8–13 min versus 9 h before.", "date_observed": "2022-10-31", "date_basis": "unassessed", "date_precision": "unassessed", "benefit_status": null, "source_collection": null, "source_entry": null, "account": "Swaminathan, López and colleagues published in npj Digital Medicine on 21 November 2023. They are at Cerebral Inc., a national tele-mental-health provider, and Stanford University School of Medicine. They described developing and deploying Crisis Message Detector 1 (CMD-1). CMD-1 is a two-stage natural-language-processing system: key-word filtering, then logistic regression. It flags patient chat messages indicating possible suicidal or homicidal ideation, domestic violence or non-suicidal self-injury. It surfaces them to Cerebral's crisis specialists via a Slack interface. The model was trained on 721 messages (32% potential crises) sent between 1 April 2021 and 1 April 2022. It was evaluated on a retrospective test set of 481 messages: AUC 0.82, sensitivity 0.99, PPV 0.35. A prospective test set had 102,471 messages from 1 to 31 October 2022 (AUC 0.98; sensitivity 0.98; PPV 0.66). 9,795 of these passed the key-word filter. In the prospective period the daily median time from message receipt to crisis-specialist triage was 8 to 13 minutes. Before deployment it averaged more than 9 hours, per Cerebral's internal analysis. False negatives reached specialists through usual channels. Seven authors report salary and equity in Cerebral and three part-time employment there. Stanford HAI's account (8 January 2024) gives the reduction as “from 10 hours to under 10 minutes” with 97% sensitivity and specificity. Those figures differ slightly from the paper's. No downstream patient outcome (hospitalization, emergency department (ED) use, attempts) is reported.", "category": "general benefit", "unexpected": false, "purpose": "Built to detect and surface crisis chat messages so that crisis specialists triage them sooner. The measured triage-time reduction is that purpose.", "system": "CMD-1 (Crisis Message Detector 1): key-word filter followed by a logistic-regression classifier on chat messages", "model_version": "CMD-1", "developer": "Cerebral Inc. with Stanford University School of Medicine collaborators", "deployer": "Cerebral Inc.", "location": "United States", "domain": "Mental health crisis response / telehealth", "segment": "Tele-mental-health chat message triage", "benefit_type": "Reduced Task Time", "taxonomy_note": null, "registry_ids": {}, "ratings": [ { "group": "personal", "depth": null, "reason": "Patients in crisis were triaged within minutes rather than hours on median. The paper reports no clinical outcome for any patient." }, { "group": "organizational", "depth": null, "reason": "The 9-hour baseline comes from Cerebral's internal analysis. The 8–13 minute figure is from the company-authored evaluation. No independent measurement exists." } ], "ai_role": { "status": "assessed", "statement": "The classifier decides which messages are surfaced to crisis specialists, who then triage them. Humans labeled the outcomes. False negatives still reached specialists through usual channels. The effect is reported by the company that built and runs the system, with Stanford co-authors. The pre-deployment baseline is an internal figure. Stanford HAI's summary gives slightly different numbers (10 hours to under 10 minutes; 97%)." }, "evidence": [ { "kind": "peer-reviewed study", "citation": "Swaminathan A, López I, Garcia Mar RA, Heist T, McClintock T, Caoili K, Grace M, Rubashkin M, Boggs M, Chen JH, Gevaert O, Lorigo D, Nock MK, Williams PA, Ahuja M, et al. (2023). Natural language processing system for rapid detection and intervention of mental health crisis chat messages. npj Digital Medicine 6 (PMC10663535). Lead authors employed by Cerebral Inc.", "title": "Natural language processing system for rapid detection and intervention of mental health crisis chat messages", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/", "date": "2023-11-21", "written_by": "makers", "quote": "The daily median time from message receipt to crisis specialist triage ranges from 8 to 13 min, compared to 9 h before the deployment of the system." }, { "kind": "peer-reviewed study", "citation": "Swaminathan A, et al. (2023), competing-interests statement of the same paper.", "title": "Natural language processing system for rapid detection and intervention of mental health crisis chat messages", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/", "date": "2023-11-21", "written_by": "makers", "quote": "The following authors report receiving a salary and owning equity in Cerebral Inc.: A.S., T.H., T.M., M.G., M.R., M.B., D.M." }, { "kind": "press release", "citation": "Kannan P (2024). Using NLP to Detect Mental Health Crises. Stanford HAI, 8 January 2024 (Stanford researchers co-authored the paper).", "title": "Using NLP to Detect Mental Health Crises", "url": "https://hai.stanford.edu/news/using-nlp-detect-mental-health-crises", "date": "2024-01-08", "written_by": "makers", "quote": "The compelling system developed here demonstrates not just an analytical result, but the much harder work of integrating that into a real workflow" } ], "replication": { "produced_by": [ "Thousands of daily patient chat messages on a telehealth platform with a crisis response team already in place", "A key-word filter followed by a logistic-regression classifier trained on 721 labeled messages", "A Slack-based workflow in which crisis specialists review and label surfaced messages" ], "must_hold": [ "Crisis specialists available to act on surfaced messages within minutes", "A high-recall filter stage, since messages that do not pass it are classified as non-crises automatically", "Message volume and language similar to the training data. The authors note the prospective PPV was 0.66" ], "echoes": [] }, "paired_incident": null, "headline": "CMD-1 cuts crisis triage from 9 hours to 8–13 minutes", "metric": "daily median receipt-to-triage time 8–13 min versus 9 h before", "comparator": { "against": "response times to patient chat messages before CMD-1 was deployed, per Cerebral's internal analysis", "before": "over 9 h on average", "after": "8 to 13 min", "basis": "measured", "quote": "The daily median time from message receipt to crisis specialist triage ranges from 8 to 13 min, compared to 9 h before the deployment of the system.", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/" }, "later": { "status": "unknown", "date": null, "note": "No source dated after the October 2022 prospective deployment reports whether CMD-1 kept running or was adopted elsewhere; the January 2024 Stanford HAI piece only restates the paper's results.", "quote": null, "url": null }, "value": null, "developer_country": "United States", "deployer_country": "United States", "unrated_because": null, "brief_notes": null, "brief": null, "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "source": null, "editor": "AIBD" }, { "date": "2026-10-21", "change": "Headline reworded to state the event without naming who claims it.", "source": null, "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against from the cited sources.", "source": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Reduced Task Time under Trustible's full taxonomy of 23 types; it was Improved Organizational Efficiency 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 and the deployer added from the organization's own site or a registry.", "source": "https://cerebral.com/privacy-policy; https://www.sec.gov/Archives/edgar/data/2083019/000208301926000001/xslFormDX01/primary_doc.xml", "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": "2026-10-22", "change": "Organization name standardized to Cerebral Inc..", "source": null, "editor": "AIBD" } ], "confidence": "claimed", "shade": "low", "claim_status": "The makers' claim", "claim_basis": "Sources: the makers' peer-reviewed study and the makers' press release. The cited evidence includes no independent source and no finding by a regulator or court.", "profile": { "case_id": "AIBD-0311", "catalog_version": "1.0.0", "source_fingerprint": "b99c2969249e6164fb497e6bf41575005746a3f4135743469b97719999e0b0f0", "collection_refs": [ { "collection_id": "aibd", "version": "snapshot-8bf7cfec9cb185aa" }, { "collection_id": "aibd", "version": "2026-10-25" } ], "source_ids": [ "AIBD-0311-source-0001", "AIBD-0311-source-0002", "AIBD-0311-source-0003" ], "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": "Cerebral Inc. with Stanford University School of Medicine collaborators", "deployer": "Cerebral Inc." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "developer", "deployer" ], "source_refs": [] }, "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": "The classifier decides which messages are surfaced to crisis specialists, who then triage them. Humans labeled the outcomes. False negatives still reached specialists through usual channels. The effect is reported by the company that built and runs the system, with Stanford co-authors. The pre-deployment baseline is an internal figure. Stanford HAI's summary gives slightly different numbers (10 hours to under 10 minutes; 97%)." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "ai_relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "category": "general benefit", "ai_role": { "status": "assessed", "statement": "The classifier decides which messages are surfaced to crisis specialists, who then triage them. Humans labeled the outcomes. False negatives still reached specialists through usual channels. The effect is reported by the company that built and runs the system, with Stanford co-authors. The pre-deployment baseline is an internal figure. Stanford HAI's summary gives slightly different numbers (10 hours to under 10 minutes; 97%)." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ai_role", "category" ], "source_refs": [] }, "review_state": "record_mapped", "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": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].display_confidence": { "state": "value_present", "value": { "kind": "structured", "data": { "confidence": "low", "evidence_word": "claimed", "claim_status": "The makers' claim", "basis": "Sources: the makers' peer-reviewed study and the makers' press release. The cited evidence includes no independent source and no finding by a regulator or court.", "interpretation": "Existing display rule preserved; the richer outcome-specific confidence question still needs review." } }, "provenance": { "kind": "curatorial", "basis": "Derived from the existing case display properties; not a new evidentiary judgment.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].rationale": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "Patients in crisis were triaged within minutes rather than hours on median. The paper reports no clinical outcome for any patient." }, { "group": "organizational", "reason": "The 9-hour baseline comes from Cerebral's internal analysis. The 8–13 minute figure is from the company-authored evaluation. No independent measurement exists." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "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", "reason": "Patients in crisis were triaged within minutes rather than hours on median. The paper reports no clinical outcome for any patient." }, { "group": "organizational", "reason": "The 9-hour baseline comes from Cerebral's internal analysis. The 8–13 minute figure is from the company-authored evaluation. No independent measurement exists." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "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": "daily median receipt-to-triage time 8–13 min versus 9 h before", "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": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "follow_up[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "later": { "status": "unknown", "note": "No source dated after the October 2022 prospective deployment reports whether CMD-1 kept running or was adopted elsewhere; the January 2024 Stanford HAI piece only restates the paper's results." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "later" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "human_oversight": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "id": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "id": "AIBD-0311" } }, "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": "Reduced Task Time" } }, "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": "Swaminathan, López and colleagues published in npj Digital Medicine on 21 November 2023. They are at Cerebral Inc., a national tele-mental-health provider, and Stanford University School of Medicine. They described developing and deploying Crisis Message Detector 1 (CMD-1). CMD-1 is a two-stage natural-language-processing system: key-word filtering, then logistic regression. It flags patient chat messages indicating possible suicidal or homicidal ideation, domestic violence or non-suicidal self-injury. It surfaces them to Cerebral's crisis specialists via a Slack interface. The model was trained on 721 messages (32% potential crises) sent between 1 April 2021 and 1 April 2022. It was evaluated on a retrospective test set of 481 messages: AUC 0.82, sensitivity 0.99, PPV 0.35. A prospective test set had 102,471 messages from 1 to 31 October 2022 (AUC 0.98; sensitivity 0.98; PPV 0.66). 9,795 of these passed the key-word filter. In the prospective period the daily median time from message receipt to crisis-specialist triage was 8 to 13 minutes. Before deployment it averaged more than 9 hours, per Cerebral's internal analysis. False negatives reached specialists through usual channels. Seven authors report salary and equity in Cerebral and three part-time employment there. Stanford HAI's account (8 January 2024) gives the reduction as “from 10 hours to under 10 minutes” with 97% sensitivity and specificity. Those figures differ slightly from the paper's. No downstream patient outcome (hospitalization, emergency department (ED) use, attempts) is reported.", "benefit_type": "Reduced Task Time" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "account", "benefit_type" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "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", "reason": "Patients in crisis were triaged within minutes rather than hours on median. The paper reports no clinical outcome for any patient." }, { "group": "organizational", "reason": "The 9-hour baseline comes from Cerebral's internal analysis. The 8–13 minute figure is from the company-authored evaluation. No independent measurement exists." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "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": "Built to detect and surface crisis chat messages so that crisis specialists triage them sooner. The measured triage-time reduction is that purpose." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "unexpected", "purpose" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "places[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "location": "United States", "developer_country": "United States", "deployer_country": "United States" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "location", "developer_country", "deployer_country" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "purpose": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "purpose": "Built to detect and surface crisis chat messages so that crisis specialists triage them sooner. The measured triage-time reduction is that purpose." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "purpose" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "record_dates": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "date_observed": "2022-10-31", "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Headline reworded to state the event without naming who claims it.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against from the cited sources.", "source": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Reduced Task Time under Trustible's full taxonomy of 23 types; it was Improved Organizational Efficiency 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 and the deployer added from the organization's own site or a registry.", "source": "https://cerebral.com/privacy-policy; https://www.sec.gov/Archives/edgar/data/2083019/000208301926000001/xslFormDX01/primary_doc.xml", "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": "2026-10-22", "change": "Organization name standardized to Cerebral Inc..", "editor": "AIBD" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "date_observed", "revisions" ], "source_refs": [] }, "review_state": "record_mapped", "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": [ "Thousands of daily patient chat messages on a telehealth platform with a crisis response team already in place", "A key-word filter followed by a logistic-regression classifier trained on 721 labeled messages", "A Slack-based workflow in which crisis specialists review and label surfaced messages" ], "must_hold": [ "Crisis specialists available to act on surfaced messages within minutes", "A high-recall filter stage, since messages that do not pass it are classified as non-crises automatically", "Message volume and language similar to the training data. The authors note the prospective PPV was 0.66" ], "echoes": [] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "revision_history[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Headline reworded to state the event without naming who claims it.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against from the cited sources.", "source": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Reduced Task Time under Trustible's full taxonomy of 23 types; it was Improved Organizational Efficiency 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 and the deployer added from the organization's own site or a registry.", "source": "https://cerebral.com/privacy-policy; https://www.sec.gov/Archives/edgar/data/2083019/000208301926000001/xslFormDX01/primary_doc.xml", "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": "2026-10-22", "change": "Organization name standardized to Cerebral Inc..", "editor": "AIBD" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "revisions" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sector": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "domain": "Mental health crisis response / telehealth", "segment": "Tele-mental-health chat message triage" } }, "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": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "sources[].citation_locator": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "evidence": [ { "kind": "peer-reviewed study", "citation": "Swaminathan A, López I, Garcia Mar RA, Heist T, McClintock T, Caoili K, Grace M, Rubashkin M, Boggs M, Chen JH, Gevaert O, Lorigo D, Nock MK, Williams PA, Ahuja M, et al. (2023). Natural language processing system for rapid detection and intervention of mental health crisis chat messages. npj Digital Medicine 6 (PMC10663535). Lead authors employed by Cerebral Inc.", "title": "Natural language processing system for rapid detection and intervention of mental health crisis chat messages", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/", "date": "2023-11-21", "written_by": "makers", "quote": "The daily median time from message receipt to crisis specialist triage ranges from 8 to 13 min, compared to 9 h before the deployment of the system." }, { "kind": "peer-reviewed study", "citation": "Swaminathan A, et al. (2023), competing-interests statement of the same paper.", "title": "Natural language processing system for rapid detection and intervention of mental health crisis chat messages", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/", "date": "2023-11-21", "written_by": "makers", "quote": "The following authors report receiving a salary and owning equity in Cerebral Inc.: A.S., T.H., T.M., M.G., M.R., M.B., D.M." }, { "kind": "press release", "citation": "Kannan P (2024). Using NLP to Detect Mental Health Crises. Stanford HAI, 8 January 2024 (Stanford researchers co-authored the paper).", "title": "Using NLP to Detect Mental Health Crises", "url": "https://hai.stanford.edu/news/using-nlp-detect-mental-health-crises", "date": "2024-01-08", "written_by": "makers", "quote": "The compelling system developed here demonstrates not just an analytical result, but the much harder work of integrating that into a real workflow" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "evidence" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].id": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "AIBD-0311-source-0001", "AIBD-0311-source-0002", "AIBD-0311-source-0003" ], "role": "Existing evidence items, in their original order" }, "provenance": { "kind": "curatorial", "basis": "Stable within the fingerprinted record version; no source content or source review has been added.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "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": "peer-reviewed study", "citation": "Swaminathan A, López I, Garcia Mar RA, Heist T, McClintock T, Caoili K, Grace M, Rubashkin M, Boggs M, Chen JH, Gevaert O, Lorigo D, Nock MK, Williams PA, Ahuja M, et al. (2023). Natural language processing system for rapid detection and intervention of mental health crisis chat messages. npj Digital Medicine 6 (PMC10663535). Lead authors employed by Cerebral Inc.", "title": "Natural language processing system for rapid detection and intervention of mental health crisis chat messages", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/", "date": "2023-11-21", "written_by": "makers", "quote": "The daily median time from message receipt to crisis specialist triage ranges from 8 to 13 min, compared to 9 h before the deployment of the system." }, { "kind": "peer-reviewed study", "citation": "Swaminathan A, et al. (2023), competing-interests statement of the same paper.", "title": "Natural language processing system for rapid detection and intervention of mental health crisis chat messages", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10663535/", "date": "2023-11-21", "written_by": "makers", "quote": "The following authors report receiving a salary and owning equity in Cerebral Inc.: A.S., T.H., T.M., M.G., M.R., M.B., D.M." }, { "kind": "press release", "citation": "Kannan P (2024). Using NLP to Detect Mental Health Crises. Stanford HAI, 8 January 2024 (Stanford researchers co-authored the paper).", "title": "Using NLP to Detect Mental Health Crises", "url": "https://hai.stanford.edu/news/using-nlp-detect-mental-health-crises", "date": "2024-01-08", "written_by": "makers", "quote": "The compelling system developed here demonstrates not just an analytical result, but the much harder work of integrating that into a real workflow" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "evidence" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].upstream_sources": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "strategic_assessments[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "strategic assessments" }, "summary": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "summary": "Two-stage NLP (keyword filter plus logistic regression) screened 102,471 chat messages in October 2022 (AUC 0.98, sensitivity 0.98); daily median receipt-to-triage time 8–13 min versus 9 h before.", "account": "Swaminathan, López and colleagues published in npj Digital Medicine on 21 November 2023. They are at Cerebral Inc., a national tele-mental-health provider, and Stanford University School of Medicine. They described developing and deploying Crisis Message Detector 1 (CMD-1). CMD-1 is a two-stage natural-language-processing system: key-word filtering, then logistic regression. It flags patient chat messages indicating possible suicidal or homicidal ideation, domestic violence or non-suicidal self-injury. It surfaces them to Cerebral's crisis specialists via a Slack interface. The model was trained on 721 messages (32% potential crises) sent between 1 April 2021 and 1 April 2022. It was evaluated on a retrospective test set of 481 messages: AUC 0.82, sensitivity 0.99, PPV 0.35. A prospective test set had 102,471 messages from 1 to 31 October 2022 (AUC 0.98; sensitivity 0.98; PPV 0.66). 9,795 of these passed the key-word filter. In the prospective period the daily median time from message receipt to crisis-specialist triage was 8 to 13 minutes. Before deployment it averaged more than 9 hours, per Cerebral's internal analysis. False negatives reached specialists through usual channels. Seven authors report salary and equity in Cerebral and three part-time employment there. Stanford HAI's account (8 January 2024) gives the reduction as “from 10 hours to under 10 minutes” with 97% sensitivity and specificity. Those figures differ slightly from the paper's. No downstream patient outcome (hospitalization, emergency department (ED) use, attempts) is reported." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "summary", "account" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].autonomy_permissions": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].component_role": { "state": "value_present", "value": { "kind": "text", "text": "The classifier selected potentially urgent messages for crisis specialists to review." }, "provenance": { "kind": "legacy_record", "basis": "Restated the mechanical task already described in the existing system and AI-role fields. No new source review is claimed.", "record_fields": [ "system", "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].deployment_configuration": { "state": "value_present", "value": { "kind": "text", "text": "The deployment used CMD-1." }, "provenance": { "kind": "legacy_record", "basis": "Separated the model, software, hardware, or operation already described in the existing record. No new source review is claimed.", "record_fields": [ "model_version", "system", "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].inputs_outputs": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].model_name": { "state": "value_present", "value": { "kind": "text", "text": "A logistic-regression classifier following a keyword filter." }, "provenance": { "kind": "legacy_record", "basis": "Separated the model, software, hardware, or operation already described in the existing record. No new source review is claimed.", "record_fields": [ "model_version", "system", "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].model_version": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "model_version": "CMD-1" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "model_version" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial", "display": { "answer": "Exact release not established.", "editor_note": "" } }, "systems[].product_name": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "system": "CMD-1 (Crisis Message Detector 1): key-word filter followed by a logistic-regression classifier on chat messages" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "system" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].provider": { "state": "value_present", "value": { "kind": "structured", "data": { "application_developer": "Cerebral Inc. with Stanford University School of Medicine collaborators" } }, "provenance": { "kind": "legacy_record", "basis": "Mapped from the existing case description without a new external source review.", "record_fields": [ "developer" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "taxonomy_crosswalks[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "title": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "title": "Cerebral's CMD-1 NLP crisis-message detector cuts median time to crisis-specialist triage from about 9 hours to 8–13 minutes in a prospective October 2022 deployment", "headline": "CMD-1 cuts crisis triage from 9 hours to 8–13 minutes" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "title", "headline" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "version": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "b99c2969249e6164fb497e6bf41575005746a3f4135743469b97719999e0b0f0" ], "role": "SHA-256 of normalized original case data" }, "provenance": { "kind": "curatorial", "basis": "Deterministic content version assigned by the local migration.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "complete" }, "workflow": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "Swaminathan, López and colleagues published in npj Digital Medicine on 21 November 2023. They are at Cerebral Inc., a national tele-mental-health provider, and Stanford University School of Medicine. They described developing and deploying Crisis Message Detector 1 (CMD-1). CMD-1 is a two-stage natural-language-processing system: key-word filtering, then logistic regression. It flags patient chat messages indicating possible suicidal or homicidal ideation, domestic violence or non-suicidal self-injury. It surfaces them to Cerebral's crisis specialists via a Slack interface. The model was trained on 721 messages (32% potential crises) sent between 1 April 2021 and 1 April 2022. It was evaluated on a retrospective test set of 481 messages: AUC 0.82, sensitivity 0.99, PPV 0.35. A prospective test set had 102,471 messages from 1 to 31 October 2022 (AUC 0.98; sensitivity 0.98; PPV 0.66). 9,795 of these passed the key-word filter. In the prospective period the daily median time from message receipt to crisis-specialist triage was 8 to 13 minutes. Before deployment it averaged more than 9 hours, per Cerebral's internal analysis. False negatives reached specialists through usual channels. Seven authors report salary and equity in Cerebral and three part-time employment there. Stanford HAI's account (8 January 2024) gives the reduction as “from 10 hours to under 10 minutes” with 97% sensitivity and specificity. Those figures differ slightly from the paper's. No downstream patient outcome (hospitalization, emergency department (ED) use, attempts) is reported.", "replication": { "produced_by": [ "Thousands of daily patient chat messages on a telehealth platform with a crisis response team already in place", "A key-word filter followed by a logistic-regression classifier trained on 721 labeled messages", "A Slack-based workflow in which crisis specialists review and label surfaced messages" ], "must_hold": [ "Crisis specialists available to act on surfaced messages within minutes", "A high-recall filter stage, since messages that do not pass it are classified as non-crises automatically", "Message volume and language similar to the training data. The authors note the prospective PPV was 0.66" ], "echoes": [] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "account", "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" } }, "summary": { "total": 91, "addressed": 91, "known": 31, "reviewed": 0, "record_mapped": 31, "not_assessed": 60, "complete": false, "by_state": { "value_present": 31, "not_reported": 0, "unresolved": 0, "not_assessed": 60, "not_applicable": 0, "withheld": 0, "source_unavailable": 0 } } } }