{"id":"AIBD-0652","title":"EMA qualifies AIM-NASH after AI-assisted pathologists scored MASH liver biopsies more accurately than pathologists reading alone","summary":"EMA qualified PathAI's AIM-NASH after a 1,481-case validation in which AI-assisted pathologists agreed better with expert panels on inflammation and ballooning.","date_observed":"2023-06-01","date_basis":"source information","date_precision":"month","benefit_status":"reported","source_collection":null,"source_entry":null,"account":"PathAI of Boston built AIM-NASH, a set of deep learning models that score liver biopsy slides for the features that define metabolic dysfunction-associated steatohepatitis (MASH) in drug trials. A pathologist reviews each AI score and accepts or rejects it. In the clinical validation that PathAI submitted to the European Medicines Agency (EMA) in June 2023, 1,481 biopsy cases from four completed trials of obeticholic acid, pegbelfermin and semaglutide were scored by panels of two expert liver pathologists with a third as tiebreaker, by individual pathologists reading alone, and by pathologists using the tool. Agreement with the panel, measured by weighted kappa, was higher with the tool for lobular inflammation (0.419 against 0.297) and hepatocellular ballooning (0.563 against 0.414), and similar for steatosis and fibrosis. EMA's human medicines committee (CHMP) endorsed this conclusion and adopted its first qualification opinion for an AI-based method on 27 February 2025, which means that the committee can accept evidence from the tool in future applications. The committee noted open questions on the clinical meaning of the gains, and the qualification covers only the locked version of the tool with one scanner model. PathAI and four drug companies funded the study, and several authors were PathAI employees.","category":"general benefit","unexpected":false,"purpose":"AIM-NASH was built to help trial pathologists score MASH biopsies with less variability. More accurate and consistent scoring is that purpose.","system":"AIM-NASH (Artificial Intelligence-Based Measurement of NASH histology; also called AIM-MASH)","model_version":null,"developer":"PathAI","deployer":"PathAI with sponsors of MASH drug trials (validation on archived biopsies from trials of obeticholic acid, pegbelfermin and semaglutide)","location":"Multinational MASH clinical trials (central pathology reading)","domain":"Drug development / pathology","segment":null,"benefit_type":"Improved Task Accuracy","taxonomy_note":null,"registry_ids":{},"ratings":[{"group":"organizational","depth":2,"reason":"Weighted kappa against the expert panel rose from 0.297 to 0.419 for lobular inflammation and from 0.414 to 0.563 for ballooning in 1,481 cases."}],"ai_role":{"status":"assessed","statement":"The validation compared AI-assisted reads with unassisted individual pathologist reads of the same 1,481 cases against the same expert panel."},"evidence":[{"kind":"regulatory document","citation":"European Medicines Agency, Committee for Medicinal Products for Human Use. Qualification opinion for Artificial Intelligence-Based Measurement of Non-alcoholic Steatohepatitis Histology in Liver Biopsies to Determine Disease Activity in NASH/MASH Clinical Trials. Adopted 27 February 2025 (EMADOC-1700519818-1761332 Corr.1).","title":"Qualification opinion for Artificial Intelligence-Based Measurement of Non-alcoholic Steatohepatitis Histology in Liver Biopsies to Determine Disease Activity in NASH/MASH Clinical Trials","url":"https://www.ema.europa.eu/en/documents/other/qualification-opinion-artificial-intelligence-based-measurement-non-alcoholic-steatohepatitis-histology-liver-biopsies-determine-disease-activity-nash-mash-clinical-trials_en.pdf","date":"2025-02-27","written_by":"independent","quote":"The Applicant concludes that the accuracy analysis demonstrated that the AI-assisted scores were superior to the manual pathologist scoring for lobular inflammation and hepatocellular ballooning and non-inferior for steatosis and fibrosis. Secondary and exploratory analysis also demonstrated improved accuracy of the AI-assisted scoring compared to manual pathologist evaluation. This overall conclusion is endorsed, but some questions on clinical meaningfulness on comparison to literature reports remain."},{"kind":"press release","citation":"European Medicines Agency. EMA qualifies first artificial intelligence tool to diagnose inflammatory liver disease (MASH) in biopsy samples. 20 March 2025.","title":"EMA qualifies first artificial intelligence tool to diagnose inflammatory liver disease (MASH) in biopsy samples","url":"https://www.ema.europa.eu/en/news/ema-qualifies-first-artificial-intelligence-tool-diagnose-inflammatory-liver-disease-mash-biopsy-samples","date":"2025-03-20","written_by":"independent","quote":"The evidence submitted to CHMP shows that AIM-NASH biopsy readings, verified by one expert pathologist, can reliably determine MASH disease activity with less variability than the current standard used in clinical trials"},{"kind":"peer-reviewed study","citation":"Pulaski H, Harrison SA, Mehta SS, et al. Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis. Nature Medicine. 2025;31:315-322. Published online 4 November 2024.","title":"Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis","url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11750710/","date":"2024-11-04","written_by":"makers","quote":"the difference in WK for AI assisted and GT compared to mean WK for IMR and GT for hepatocellular ballooning was 0.15 (95% CI, 0.11-0.19; non-inferiority P < 0.0001) and for lobular inflammation was 0.12 (95% CI, 0.08-0.17; non-inferiority P < 0.0001)"}],"replication":{"produced_by":["Slides were scanned on the Aperio AT2 scanner.","A trained liver pathologist reviewed every AI score and could reject it.","The model was locked before validation."],"must_hold":["Users run the locked version of the tool on slides from the same scanner model.","Major changes to the model come with new validation."],"echoes":[]},"paired_incident":null,"headline":"Europe's medicines regulator accepts *AIM-NASH* for biopsy scoring","metric":"hepatocellular ballooning (0.563 against 0.414)","comparator":{"against":"Individual pathologists reading without the tool, scored against the same expert panel","before":"Mean weighted kappa of unassisted reads","after":"Weighted kappa higher by 0.15 for ballooning and 0.12 for lobular inflammation","basis":"measured","quote":"the difference in WK for AI assisted and GT compared to mean WK for IMR and GT for hepatocellular ballooning was 0.15 (95% CI, 0.11-0.19; non-inferiority P < 0.0001) and for lobular inflammation was 0.12 (95% CI, 0.08-0.17; non-inferiority P < 0.0001)","url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11750710/"},"later":null,"value":null,"developer_country":"United States","deployer_country":"United States","unrated_because":null,"brief_notes":null,"brief":null,"revisions":[{"date":"2026-10-29","change":"Added the case.","source":"https://www.ema.europa.eu/en/documents/other/qualification-opinion-artificial-intelligence-based-measurement-non-alcoholic-steatohepatitis-histology-liver-biopsies-determine-disease-activity-nash-mash-clinical-trials_en.pdf","editor":"AIBD"}],"confidence":"found","shade":"high","claim_status":"Found by a regulator","claim_basis":"Sources: one independent regulatory document, one independent press release and the makers' peer-reviewed study. The cited evidence includes no independent study or report.","case_jurisdictions":[],"profile":{"case_id":"AIBD-0652","catalog_version":"1.0.0","source_fingerprint":"024c767887129cbc5221c8e03f669bbee3aff3dd0dfa09accdbef68250b9f0a2","collection_refs":[{"collection_id":"aibd","version":"2026-10-29"},{"collection_id":"querist","version":"2026-10-25"}],"source_ids":["AIBD-0652-source-0001","AIBD-0652-source-0002","AIBD-0652-source-0003"],"families":{"strategic assessments":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"Editorial assignment.","review_state":"not_assessed","coverage":"partial","record_ids":[]},"evaluations":{"state":"value_present","value":{"kind":"identifiers","identifiers":["AIBD-0652-evaluation-1"],"role":"Evaluations of the benefit"},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":[],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"partial","record_ids":["AIBD-0652-evaluation-1"]},"monetary observations":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"Editorial assignment.","review_state":"not_assessed","coverage":"partial","record_ids":[]},"institutional decisions":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"Editorial assignment.","review_state":"not_assessed","coverage":"partial","record_ids":[]}},"fields":{"actors[]":{"state":"value_present","value":{"kind":"record_fields","fields":{"developer":"PathAI","deployer":"PathAI with sponsors of MASH drug trials (validation on archived biopsies from trials of obeticholic acid, pegbelfermin and semaglutide)"}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["developer","deployer"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"actors[].ownership_control":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"ai_contribution":{"state":"value_present","value":{"kind":"record_fields","fields":{"ai_role":{"status":"assessed","statement":"The validation compared AI-assisted reads with unassisted individual pathologist reads of the same 1,481 cases against the same expert panel."}}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","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 validation compared AI-assisted reads with unassisted individual pathologist reads of the same 1,481 cases against the same expert panel."}}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["ai_role","category"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"assessments[].alternatives":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"assessments[].assessor_date":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"assessments[].depth":{"state":"value_present","value":{"kind":"record_fields","fields":{"ratings":[{"group":"organizational","depth":2,"reason":"Weighted kappa against the expert panel rose from 0.297 to 0.419 for lobular inflammation and from 0.414 to 0.563 for ballooning in 1,481 cases."}]}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["ratings"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"assessments[].display_confidence":{"state":"value_present","value":{"kind":"structured","data":{"confidence":"high","evidence_word":"found","claim_status":"Found by a regulator","basis":"Sources: one independent regulatory document, one independent press release and the makers' peer-reviewed study. The cited evidence includes no independent study or report.","interpretation":"Existing display rule preserved; the richer outcome-specific confidence question still needs review."}},"provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"assessments[].rationale":{"state":"value_present","value":{"kind":"record_fields","fields":{"ratings":[{"group":"organizational","depth":2,"reason":"Weighted kappa against the expert panel rose from 0.297 to 0.419 for lobular inflammation and from 0.414 to 0.563 for ballooning in 1,481 cases."}]}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["ratings"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"assessments[].rubric_version":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"assessments[].status_basis":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"assessments[].target":{"state":"value_present","value":{"kind":"record_fields","fields":{"ratings":[{"group":"organizational","depth":2,"reason":"Weighted kappa against the expert panel rose from 0.297 to 0.419 for lobular inflammation and from 0.414 to 0.563 for ballooning in 1,481 cases."}]}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["ratings"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"availability":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"brief":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"case_kind":{"state":"value_present","value":{"kind":"structured","data":{"classification":"evaluation or study","answer":"The case describes an evaluation or a study. A regulator's qualification of a validated method.","scope":"The period and activity described in the case."}},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["account","evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"The case describes an evaluation or a study. A regulator's qualification of a validated method.","inferred":false}},"case_links[]":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Compared with the incidents in the AI Incident Database snapshot of 26 October 2026.","record_fields":["paired_incident"],"source_refs":[]},"reason":"No incident in the AI Incident Database snapshot of 26 October 2026 concerns the same kind of system harming the same kind of stakeholder.","review_state":"reviewed","coverage":"partial"},"claims[].evidence_links":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"claims[].evidence_strength":{"state":"value_present","value":{"kind":"structured","data":{"answer":"Found by a regulator. Sources: one independent regulatory document, one independent press release and the makers' peer-reviewed study. The cited evidence includes no independent study or report.","evidence_word":"found","claim_status":"Found by a regulator"}},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001","AIBD-0652-source-0002","AIBD-0652-source-0003"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Found by a regulator. Sources: one independent regulatory document, one independent press release and the makers' peer-reviewed study. The cited evidence includes no independent study or report.","inferred":false}},"claims[].missingness":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"claims[].proposition":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"cross_border_flows[]":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"decisions[].action_outcome":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"institutional decisions"},"decisions[].grounds":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"institutional decisions"},"decisions[].institution_task":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"institutional decisions"},"decisions[].success_criterion":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"institutional decisions"},"deployment_stage":{"state":"value_present","value":{"kind":"structured","data":{"classification":"laboratory test","answer":"The system was tested in a laboratory. The validation re-read archived biopsy slides from completed trials.","scope":"The period and activity described in the case."}},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["account","evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"The system was tested in a laboratory. The validation re-read archived biopsy slides from completed trials.","inferred":false}},"economics[].amount":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].costs[]":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].counterfactual":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].currency_price_basis":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].gross_net":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].measure_type":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].period_unit":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].realization":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].recipient_payer":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].return_payback":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"economics[].valuation_method":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"monetary observations"},"evaluations[].ai_uplift":{"state":"value_present","value":{"kind":"text","text":"Weighted kappa higher by 0.12 to 0.15 for inflammation and ballooning."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Weighted kappa higher by 0.12 to 0.15 for inflammation and ballooning.","inferred":false}},"evaluations[].comparator":{"state":"value_present","value":{"kind":"text","text":"Individual manual reads of the same cases."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Individual manual reads of the same cases.","inferred":false}},"evaluations[].design":{"state":"value_present","value":{"kind":"text","text":"Controlled observational."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Controlled observational.","inferred":false}},"evaluations[].effect":{"state":"value_present","value":{"kind":"text","text":"Lobular inflammation 0.419 against 0.297; ballooning 0.563 against 0.414; steatosis and fibrosis similar."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Lobular inflammation 0.419 against 0.297; ballooning 0.563 against 0.414; steatosis and fibrosis similar.","inferred":false}},"evaluations[].exposure":{"state":"value_present","value":{"kind":"text","text":"One AI-assisted read per case."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"One AI-assisted read per case.","inferred":false}},"evaluations[].id":{"state":"value_present","value":{"kind":"identifiers","identifiers":["AIBD-0652-evaluation-1"],"role":"Evaluations of the benefit"},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Controlled observational.","inferred":false}},"evaluations[].measurement_method":{"state":"value_present","value":{"kind":"text","text":"Weighted kappa of AI-assisted reads and of individual manual reads against panels of two expert pathologists with a tiebreaker."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Weighted kappa of AI-assisted reads and of individual manual reads against panels of two expert pathologists with a tiebreaker.","inferred":false}},"evaluations[].metric":{"state":"value_present","value":{"kind":"text","text":"Weighted kappa against the consensus panel."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Weighted kappa against the consensus panel.","inferred":false}},"evaluations[].reproduction_materials":{"state":"value_present","value":{"kind":"text","text":"Analysis code on GitHub (Path-AI/NASH_DDT_Manuscript)."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Analysis code on GitHub (Path-AI/NASH_DDT_Manuscript).","inferred":false}},"evaluations[].setting_sample":{"state":"value_present","value":{"kind":"text","text":"1,481 cases from four completed MASH trials (three phase 2 and one phase 3)."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"1,481 cases from four completed MASH trials (three phase 2 and one phase 3).","inferred":false}},"evaluations[].uncertainty_limitations":{"state":"value_present","value":{"kind":"text","text":"Clinical meaning of the gains questioned by CHMP; locked model and one scanner model; study funded by PathAI and drug companies."},"provenance":{"kind":"source_review","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":["AIBD-0652-source-0001"],"reviewed_on":"2026-10-29"},"review_state":"reviewed","coverage":"complete","display":{"answer":"Clinical meaning of the gains questioned by CHMP; locked model and one scanner model; study funded by PathAI and drug companies.","inferred":false}},"external_references[]":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"follow_up[]":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"human_oversight":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"id":{"state":"value_present","value":{"kind":"record_fields","fields":{"id":"AIBD-0652"}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["id"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"infrastructure_dependencies[]":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"outcomes[].beneficiaries":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"outcomes[].beneficiary_count":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"outcomes[].benefit_type":{"state":"value_present","value":{"kind":"record_fields","fields":{"benefit_type":"Improved Task Accuracy"}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["benefit_type"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"outcomes[].claim":{"state":"value_present","value":{"kind":"record_fields","fields":{"account":"PathAI of Boston built AIM-NASH, a set of deep learning models that score liver biopsy slides for the features that define metabolic dysfunction-associated steatohepatitis (MASH) in drug trials. A pathologist reviews each AI score and accepts or rejects it. In the clinical validation that PathAI submitted to the European Medicines Agency (EMA) in June 2023, 1,481 biopsy cases from four completed trials of obeticholic acid, pegbelfermin and semaglutide were scored by panels of two expert liver pathologists with a third as tiebreaker, by individual pathologists reading alone, and by pathologists using the tool. Agreement with the panel, measured by weighted kappa, was higher with the tool for lobular inflammation (0.419 against 0.297) and hepatocellular ballooning (0.563 against 0.414), and similar for steatosis and fibrosis. EMA's human medicines committee (CHMP) endorsed this conclusion and adopted its first qualification opinion for an AI-based method on 27 February 2025, which means that the committee can accept evidence from the tool in future applications. The committee noted open questions on the clinical meaning of the gains, and the qualification covers only the locked version of the tool with one scanner model. PathAI and four drug companies funded the study, and several authors were PathAI employees.","benefit_type":"Improved Task Accuracy"}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["account","benefit_type"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"outcomes[].distribution":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"outcomes[].duration":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"outcomes[].id":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"outcomes[].stakeholder_group":{"state":"value_present","value":{"kind":"record_fields","fields":{"ratings":[{"group":"organizational","depth":2,"reason":"Weighted kappa against the expert panel rose from 0.297 to 0.419 for lobular inflammation and from 0.414 to 0.563 for ballooning in 1,481 cases."}]}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["ratings"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"outcomes[].status":{"state":"value_present","value":{"kind":"record_fields","fields":{"benefit_status":"reported"}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["benefit_status"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"outcomes[].tradeoffs":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"outcomes[].unexpected":{"state":"value_present","value":{"kind":"record_fields","fields":{"unexpected":false,"purpose":"AIM-NASH was built to help trial pathologists score MASH biopsies with less variability. More accurate and consistent scoring is that purpose."}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["unexpected","purpose"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"places[]":{"state":"value_present","value":{"kind":"record_fields","fields":{"location":"Multinational MASH clinical trials (central pathology reading)","developer_country":"United States","deployer_country":"United States"}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","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":"AIM-NASH was built to help trial pathologists score MASH biopsies with less variability. More accurate and consistent scoring is that purpose."}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["purpose"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"record_dates":{"state":"value_present","value":{"kind":"record_fields","fields":{"date_observed":"2023-06-01","date_basis":"source information","date_precision":"month","revisions":[{"date":"2026-10-29","change":"Added the case.","source":"https://www.ema.europa.eu/en/documents/other/qualification-opinion-artificial-intelligence-based-measurement-non-alcoholic-steatohepatitis-histology-liver-biopsies-determine-disease-activity-nash-mash-clinical-trials_en.pdf","editor":"AIBD"}]}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["date_observed","date_basis","date_precision","revisions"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"replication.attempts[]":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"replication.conditions":{"state":"value_present","value":{"kind":"record_fields","fields":{"replication":{"produced_by":["Slides were scanned on the Aperio AT2 scanner.","A trained liver pathologist reviewed every AI score and could reject it.","The model was locked before validation."],"must_hold":["Users run the locked version of the tool on slides from the same scanner model.","Major changes to the model come with new validation."],"echoes":[]}}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["replication"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"revision_history[]":{"state":"value_present","value":{"kind":"record_fields","fields":{"revisions":[{"date":"2026-10-29","change":"Added the case.","source":"https://www.ema.europa.eu/en/documents/other/qualification-opinion-artificial-intelligence-based-measurement-non-alcoholic-steatohepatitis-histology-liver-biopsies-determine-disease-activity-nash-mash-clinical-trials_en.pdf","editor":"AIBD"}]}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["revisions"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"sector":{"state":"value_present","value":{"kind":"record_fields","fields":{"domain":"Drug development / pathology"}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["domain"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"sources[].access_version":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"sources[].citation_locator":{"state":"value_present","value":{"kind":"record_fields","fields":{"evidence":[{"kind":"regulatory document","citation":"European Medicines Agency, Committee for Medicinal Products for Human Use. Qualification opinion for Artificial Intelligence-Based Measurement of Non-alcoholic Steatohepatitis Histology in Liver Biopsies to Determine Disease Activity in NASH/MASH Clinical Trials. Adopted 27 February 2025 (EMADOC-1700519818-1761332 Corr.1).","title":"Qualification opinion for Artificial Intelligence-Based Measurement of Non-alcoholic Steatohepatitis Histology in Liver Biopsies to Determine Disease Activity in NASH/MASH Clinical Trials","url":"https://www.ema.europa.eu/en/documents/other/qualification-opinion-artificial-intelligence-based-measurement-non-alcoholic-steatohepatitis-histology-liver-biopsies-determine-disease-activity-nash-mash-clinical-trials_en.pdf","date":"2025-02-27","written_by":"independent","quote":"The Applicant concludes that the accuracy analysis demonstrated that the AI-assisted scores were superior to the manual pathologist scoring for lobular inflammation and hepatocellular ballooning and non-inferior for steatosis and fibrosis. Secondary and exploratory analysis also demonstrated improved accuracy of the AI-assisted scoring compared to manual pathologist evaluation. This overall conclusion is endorsed, but some questions on clinical meaningfulness on comparison to literature reports remain."},{"kind":"press release","citation":"European Medicines Agency. EMA qualifies first artificial intelligence tool to diagnose inflammatory liver disease (MASH) in biopsy samples. 20 March 2025.","title":"EMA qualifies first artificial intelligence tool to diagnose inflammatory liver disease (MASH) in biopsy samples","url":"https://www.ema.europa.eu/en/news/ema-qualifies-first-artificial-intelligence-tool-diagnose-inflammatory-liver-disease-mash-biopsy-samples","date":"2025-03-20","written_by":"independent","quote":"The evidence submitted to CHMP shows that AIM-NASH biopsy readings, verified by one expert pathologist, can reliably determine MASH disease activity with less variability than the current standard used in clinical trials"},{"kind":"peer-reviewed study","citation":"Pulaski H, Harrison SA, Mehta SS, et al. Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis. Nature Medicine. 2025;31:315-322. Published online 4 November 2024.","title":"Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis","url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11750710/","date":"2024-11-04","written_by":"makers","quote":"the difference in WK for AI assisted and GT compared to mean WK for IMR and GT for hepatocellular ballooning was 0.15 (95% CI, 0.11-0.19; non-inferiority P < 0.0001) and for lobular inflammation was 0.12 (95% CI, 0.08-0.17; non-inferiority P < 0.0001)"}]}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"sources[].id":{"state":"value_present","value":{"kind":"identifiers","identifiers":["AIBD-0652-source-0001","AIBD-0652-source-0002","AIBD-0652-source-0003"],"role":"Existing evidence items, in their original order"},"provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"review_state":"record_mapped","coverage":"complete"},"sources[].language":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"sources[].relationship":{"state":"value_present","value":{"kind":"record_fields","fields":{"evidence":[{"kind":"regulatory document","citation":"European Medicines Agency, Committee for Medicinal Products for Human Use. Qualification opinion for Artificial Intelligence-Based Measurement of Non-alcoholic Steatohepatitis Histology in Liver Biopsies to Determine Disease Activity in NASH/MASH Clinical Trials. Adopted 27 February 2025 (EMADOC-1700519818-1761332 Corr.1).","title":"Qualification opinion for Artificial Intelligence-Based Measurement of Non-alcoholic Steatohepatitis Histology in Liver Biopsies to Determine Disease Activity in NASH/MASH Clinical Trials","url":"https://www.ema.europa.eu/en/documents/other/qualification-opinion-artificial-intelligence-based-measurement-non-alcoholic-steatohepatitis-histology-liver-biopsies-determine-disease-activity-nash-mash-clinical-trials_en.pdf","date":"2025-02-27","written_by":"independent","quote":"The Applicant concludes that the accuracy analysis demonstrated that the AI-assisted scores were superior to the manual pathologist scoring for lobular inflammation and hepatocellular ballooning and non-inferior for steatosis and fibrosis. Secondary and exploratory analysis also demonstrated improved accuracy of the AI-assisted scoring compared to manual pathologist evaluation. This overall conclusion is endorsed, but some questions on clinical meaningfulness on comparison to literature reports remain."},{"kind":"press release","citation":"European Medicines Agency. EMA qualifies first artificial intelligence tool to diagnose inflammatory liver disease (MASH) in biopsy samples. 20 March 2025.","title":"EMA qualifies first artificial intelligence tool to diagnose inflammatory liver disease (MASH) in biopsy samples","url":"https://www.ema.europa.eu/en/news/ema-qualifies-first-artificial-intelligence-tool-diagnose-inflammatory-liver-disease-mash-biopsy-samples","date":"2025-03-20","written_by":"independent","quote":"The evidence submitted to CHMP shows that AIM-NASH biopsy readings, verified by one expert pathologist, can reliably determine MASH disease activity with less variability than the current standard used in clinical trials"},{"kind":"peer-reviewed study","citation":"Pulaski H, Harrison SA, Mehta SS, et al. Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis. Nature Medicine. 2025;31:315-322. Published online 4 November 2024.","title":"Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis","url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11750710/","date":"2024-11-04","written_by":"makers","quote":"the difference in WK for AI assisted and GT compared to mean WK for IMR and GT for hepatocellular ballooning was 0.15 (95% CI, 0.11-0.19; non-inferiority P < 0.0001) and for lobular inflammation was 0.12 (95% CI, 0.08-0.17; non-inferiority P < 0.0001)"}]}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["evidence"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"sources[].upstream_sources":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"strategic_assessments[]":{"state":"unresolved","review_state":"not_assessed","coverage":"partial","family":"strategic assessments"},"summary":{"state":"value_present","value":{"kind":"record_fields","fields":{"summary":"EMA qualified PathAI's AIM-NASH after a 1,481-case validation in which AI-assisted pathologists agreed better with expert panels on inflammation and ballooning.","account":"PathAI of Boston built AIM-NASH, a set of deep learning models that score liver biopsy slides for the features that define metabolic dysfunction-associated steatohepatitis (MASH) in drug trials. A pathologist reviews each AI score and accepts or rejects it. In the clinical validation that PathAI submitted to the European Medicines Agency (EMA) in June 2023, 1,481 biopsy cases from four completed trials of obeticholic acid, pegbelfermin and semaglutide were scored by panels of two expert liver pathologists with a third as tiebreaker, by individual pathologists reading alone, and by pathologists using the tool. Agreement with the panel, measured by weighted kappa, was higher with the tool for lobular inflammation (0.419 against 0.297) and hepatocellular ballooning (0.563 against 0.414), and similar for steatosis and fibrosis. EMA's human medicines committee (CHMP) endorsed this conclusion and adopted its first qualification opinion for an AI-based method on 27 February 2025, which means that the committee can accept evidence from the tool in future applications. The committee noted open questions on the clinical meaning of the gains, and the qualification covers only the locked version of the tool with one scanner model. PathAI and four drug companies funded the study, and several authors were PathAI employees."}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["summary","account"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"systems[].autonomy_permissions":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"systems[].component_role":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"systems[].deployment_configuration":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"systems[].inputs_outputs":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"systems[].model_name":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"systems[].model_version":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"systems[].product_name":{"state":"value_present","value":{"kind":"record_fields","fields":{"system":"AIM-NASH (Artificial Intelligence-Based Measurement of NASH histology; also called AIM-MASH)"}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["system"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"systems[].provider":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"taxonomy_crosswalks[]":{"state":"unresolved","provenance":{"kind":"curatorial","basis":"Editorial assignment.","record_fields":[],"source_refs":[]},"reason":"This is an explicit unresolved assignment: the sources on record do not settle this question.","review_state":"not_assessed","coverage":"partial"},"title":{"state":"value_present","value":{"kind":"record_fields","fields":{"title":"EMA qualifies AIM-NASH after AI-assisted pathologists scored MASH liver biopsies more accurately than pathologists reading alone","headline":"Europe's medicines regulator accepts *AIM-NASH* for biopsy scoring"}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["title","headline"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"},"version":{"state":"value_present","value":{"kind":"identifiers","identifiers":["26ea130afba63e8023bd8a83e2e4c427a25e20ea49024399613c22912c8cca76"],"role":"SHA-256 of the complete public case and its assessments"},"provenance":{"kind":"curatorial","basis":"SHA-256 of the public case, its assessments, and its displayed answers and notes, excluding its own identifier and the derived coverage summary.","record_fields":[],"source_refs":[]},"review_state":"record_mapped","coverage":"complete"},"workflow":{"state":"value_present","value":{"kind":"record_fields","fields":{"account":"PathAI of Boston built AIM-NASH, a set of deep learning models that score liver biopsy slides for the features that define metabolic dysfunction-associated steatohepatitis (MASH) in drug trials. A pathologist reviews each AI score and accepts or rejects it. In the clinical validation that PathAI submitted to the European Medicines Agency (EMA) in June 2023, 1,481 biopsy cases from four completed trials of obeticholic acid, pegbelfermin and semaglutide were scored by panels of two expert liver pathologists with a third as tiebreaker, by individual pathologists reading alone, and by pathologists using the tool. Agreement with the panel, measured by weighted kappa, was higher with the tool for lobular inflammation (0.419 against 0.297) and hepatocellular ballooning (0.563 against 0.414), and similar for steatosis and fibrosis. EMA's human medicines committee (CHMP) endorsed this conclusion and adopted its first qualification opinion for an AI-based method on 27 February 2025, which means that the committee can accept evidence from the tool in future applications. The committee noted open questions on the clinical meaning of the gains, and the qualification covers only the locked version of the tool with one scanner model. PathAI and four drug companies funded the study, and several authors were PathAI employees.","replication":{"produced_by":["Slides were scanned on the Aperio AT2 scanner.","A trained liver pathologist reviewed every AI score and could reject it.","The model was locked before validation."],"must_hold":["Users run the locked version of the tool on slides from the same scanner model.","Major changes to the model come with new validation."],"echoes":[]}}},"provenance":{"kind":"legacy_record","basis":"Editorial assignment.","record_fields":["account","replication"],"source_refs":[]},"review_state":"record_mapped","coverage":"partial"}},"summary":{"total":91,"addressed":91,"known":41,"reviewed":15,"reviewed_complete":14,"reviewed_partial":1,"record_mapped":27,"review_not_assessed":49,"not_assessed":0,"complete":false,"by_state":{"value_present":41,"not_reported":0,"unresolved":50,"not_assessed":0,"not_applicable":0,"withheld":0,"source_unavailable":0}}},"presentation_version":"0fcb5feb117df5a08b2a60b5b0796c98afbd938a9fd7e3058b231e1aca3cf693"}