{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007376173,0.0002871972,0.0004956929,0.0005668704,0.0001539462,0.0001463057,0.0001683171,0.000464429,0.0005024642],"category_scores_gemma":[0.003633543,0.0002177855,0.0001308934,0.001786173,0.0004765055,0.0002576339,0.00004735833,0.001337837,0.001014235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003455799,"about_ca_system_score_gemma":0.0005345308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005351945,"about_ca_topic_score_gemma":0.00008610946,"domain_scores_codex":[0.9969593,0.00005375577,0.001018229,0.0006033927,0.0007986496,0.0005666313],"domain_scores_gemma":[0.9973114,0.001155195,0.00007359081,0.0004099992,0.000449642,0.0006001411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001563144,0.0001276165,0.001240528,0.0007771477,0.00005740532,0.0002010598,0.002846746,0.00000412589,0.0003816425,0.05424939,0.007216171,0.9327419],"study_design_scores_gemma":[0.0002249524,0.01240295,0.003965769,0.01172115,0.0008069801,0.001935498,0.04031467,0.0363527,0.05456051,0.4901715,0.3453718,0.002171542],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2888414,0.01800204,0.03460224,0.6161785,0.01158157,0.001993134,0.00006959337,0.002016177,0.02671537],"genre_scores_gemma":[0.9905593,0.0004510373,0.0002225588,0.004611595,0.002955832,0.00004071184,0.0001840744,0.00005337136,0.0009215685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9305703,"threshold_uncertainty_score":0.9997636,"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."}}