{"id":"W3004164101","doi":"10.2196/15791","title":"Improving Clinical Translation of Machine Learning Approaches Through Clinician-Tailored Visual Displays of Black Box Algorithms: Development and Validation","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Interpretability; Decision tree; Random forest; Machine learning; Black box; Artificial intelligence; Computer science; Algorithm; Regression; Medicine; Data mining; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03844894,0.001925447,0.0006092155,0.0018068,0.0004320792,0.004236143,0.002540186,0.002007029,0.01001562],"category_scores_gemma":[0.1552878,0.0007023264,0.001259917,0.0006935222,0.001163514,0.00241606,0.003346832,0.001981005,0.002082361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009070565,"about_ca_system_score_gemma":0.001926921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001446663,"about_ca_topic_score_gemma":0.00100652,"domain_scores_codex":[0.9862088,0.01043633,0.0006794477,0.0009598861,0.00149337,0.0002222994],"domain_scores_gemma":[0.8788115,0.09514343,0.003254933,0.009737351,0.01191332,0.001139456],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002889369,0.00119778,0.01611699,0.001259888,0.0003127832,0.0007375108,0.003296316,0.1044431,0.02003927,0.01677791,0.01824914,0.81468],"study_design_scores_gemma":[0.0009338201,0.001600304,0.007728411,0.001067017,0.0001138138,0.0004881069,0.0005225309,0.9069512,0.03822302,0.02615929,0.0159989,0.000213512],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07204597,0.0007751206,0.9119946,0.001896161,0.0002859183,0.00118017,0.0007376455,0.008506112,0.002578228],"genre_scores_gemma":[0.2287378,0.0004041991,0.7667167,0.0003746246,0.00009689358,0.001130597,0.0005844607,0.001200861,0.0007539088],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03844894,"threshold_uncertainty_score":0.2033399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1017864805668049,"score_gpt":0.372068754066446,"score_spread":0.2702822734996411,"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."}}