{"id":"W4407730739","doi":"10.1146/annurev-biodatasci-103123-095824","title":"Evaluation and Regulation of Artificial Intelligence Medical Devices for Clinical Decision Support","year":2025,"lang":"en","type":"review","venue":"Annual Review of Biomedical Data Science","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Health Economics","funders":"National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute","keywords":"Enthusiasm; Optimism; Health care; Equity (law); Patient safety; Risk analysis (engineering); Psychology; Knowledge management; Business; Computer science; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03817644,0.0002477588,0.002027908,0.0004861519,0.0001149507,0.00001608645,0.001253354,0.0004389173,0.0003431887],"category_scores_gemma":[0.09404419,0.000173689,0.0002523796,0.002076009,0.002277711,0.0004172737,0.0005669814,0.0003450149,0.00001439774],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008511553,"about_ca_system_score_gemma":0.01725635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004156246,"about_ca_topic_score_gemma":0.00001765703,"domain_scores_codex":[0.9910645,0.000356738,0.004015661,0.001022302,0.003221459,0.000319353],"domain_scores_gemma":[0.9861767,0.005944639,0.001715026,0.001853242,0.003626081,0.0006842789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001518547,0.0001743758,0.000004267032,0.1026853,0.00002411968,5.683067e-7,0.00002100952,4.476068e-9,2.528358e-7,0.0003668522,0.003342926,0.8933651],"study_design_scores_gemma":[0.00002317589,0.0005235182,0.00003330183,0.2549097,0.001815797,0.00002904029,0.00008961376,0.0009520686,0.000006677214,0.0008178568,0.7406604,0.0001388303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000006716912,0.985735,0.008940015,0.0009533594,0.001063186,0.002654212,0.0005568013,0.00001081145,0.00007987845],"genre_scores_gemma":[0.00004771687,0.9913415,0.005789381,0.0004212568,0.0003629532,0.00007807289,0.001937715,0.00001030769,0.00001108518],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8932263,"threshold_uncertainty_score":0.9903998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5002733274395434,"score_gpt":0.6473847839691036,"score_spread":0.1471114565295601,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}