{"id":"W4402453991","doi":"10.1038/s41746-024-01242-1","title":"Ethical debates amidst flawed healthcare artificial intelligence metrics","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Institute on Minority Health and Health Disparities; National Institute of Biomedical Imaging and Bioengineering; Fogarty International Center; Gordon and Betty Moore Foundation; National Heart, Lung, and Blood Institute; Radiological Society of North America; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Health care; Engineering ethics; Psychology; Political science; Sociology; Artificial intelligence; Computer science; Engineering; Law","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3978674,0.001110993,0.001584696,0.003834266,0.004496236,0.01914429,0.005416029,0.01272058,0.002005983],"category_scores_gemma":[0.5630214,0.0009124381,0.001027072,0.003067197,0.03720783,0.017988,0.01008878,0.020548,0.0009983501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009107567,"about_ca_system_score_gemma":0.01795375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002566346,"about_ca_topic_score_gemma":0.001946027,"domain_scores_codex":[0.5581716,0.3146172,0.02379213,0.01265866,0.08633924,0.004421117],"domain_scores_gemma":[0.364858,0.4802059,0.02530243,0.04582737,0.07660731,0.007199039],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007663502,0.00006319265,0.002788366,0.0002418869,0.00007300574,0.0002199443,0.00619418,0.001734319,0.0003339102,0.8888524,0.03961557,0.05980665],"study_design_scores_gemma":[0.00005639558,0.00007866514,0.001204177,0.001379222,0.00003751778,0.0004321181,0.001870509,0.003960435,0.0007841329,0.9137074,0.07639457,0.00009496196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.008786384,0.006366972,0.09094115,0.8643761,0.002732158,0.0002009066,0.000170131,0.0001915702,0.02623465],"genre_scores_gemma":[0.5628839,0.006679392,0.1905951,0.2257325,0.00837877,0.001076579,0.0003032145,0.0004509867,0.003899551],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6021326,"threshold_uncertainty_score":0.7425367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2500806651770794,"score_gpt":0.4727379784701678,"score_spread":0.2226573132930884,"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."}}