{"id":"W4387001850","doi":"10.1001/jamanetworkopen.2023.35377","title":"APPRAISE-AI Tool for Quantitative Evaluation of AI Studies for Clinical Decision Support","year":2023,"lang":"en","type":"review","venue":"JAMA Network Open","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":113,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Princess Margaret Cancer Centre; Public Health Ontario; Hospital for Sick Children; SickKids Foundation; University Health Network; University of Toronto","funders":"","keywords":"Inter-rater reliability; Artificial intelligence; Medicine; Reliability (semiconductor); Machine learning; Medical physics; Computer science; Psychology; Rating scale","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":[],"category_scores_codex":[0.01728093,0.0002871973,0.002531932,0.000128011,0.0001834452,0.00006956689,0.000377707,0.0005240655,0.00006527459],"category_scores_gemma":[0.01925037,0.0002190243,0.0006774961,0.0005172077,0.0001020299,0.0001991958,0.0001779025,0.0004165173,0.0001059731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002146877,"about_ca_system_score_gemma":0.003363909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004293845,"about_ca_topic_score_gemma":0.00009694546,"domain_scores_codex":[0.9952176,0.0005789141,0.002702518,0.0006149404,0.0005103687,0.0003756921],"domain_scores_gemma":[0.979421,0.0153379,0.001127998,0.0005660374,0.003431453,0.000115598],"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":[0.0004208506,0.00007777959,0.0001188442,0.007532337,0.0004456213,4.71191e-7,0.0002479254,0.00002596594,5.165209e-9,0.0008279107,0.2627817,0.7275206],"study_design_scores_gemma":[0.0003037937,0.00144046,0.00008833684,0.02946427,0.003735016,0.000003578336,0.0006336899,0.001802864,6.759485e-7,0.01462229,0.9476868,0.0002182211],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00008648203,0.969969,0.005035942,0.001892367,0.004095429,0.01866149,0.0001047587,0.00003020237,0.0001243599],"genre_scores_gemma":[0.00002932564,0.9791031,0.009948167,0.0007140707,0.003027326,0.005354065,0.001064335,0.00008079603,0.0006787598],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7273024,"threshold_uncertainty_score":0.9890109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8642618477117467,"score_gpt":0.7294409870398627,"score_spread":0.134820860671884,"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."}}