{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001587211,0.0001684583,0.0004578779,0.00006192554,0.00008346955,0.00003700772,0.000448288,0.0002483205,0.00001349589],"category_scores_gemma":[0.0008968259,0.000145695,0.00007679895,0.0003346237,0.0002005642,0.0005770955,0.0002645422,0.0007792011,0.000006881359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001792369,"about_ca_system_score_gemma":0.0002946271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002110515,"about_ca_topic_score_gemma":0.000003203575,"domain_scores_codex":[0.9964108,0.0002461351,0.00200852,0.000203407,0.0009002464,0.0002308947],"domain_scores_gemma":[0.9979897,0.0005903593,0.0008843114,0.0001809481,0.00009844607,0.0002562875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004972984,0.0001363445,0.02473295,0.002064173,0.00004905985,0.000002652108,0.07777651,0.0007929691,0.000007836938,0.001785231,0.0000314731,0.8925711],"study_design_scores_gemma":[0.0007917385,0.0004201231,0.002346618,0.0001205018,0.00001043982,0.000003626019,0.001029487,0.9937555,0.0003376502,0.00005143141,0.0009895801,0.0001432781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.205334,0.00007489707,0.7925999,0.001205247,0.00009384119,0.000345996,0.000002029793,0.00008832662,0.0002557877],"genre_scores_gemma":[0.7193834,0.00004388617,0.2800322,0.0003831613,0.0000858057,0.00001018214,0.00004756814,0.00001042918,0.000003367931],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9929625,"threshold_uncertainty_score":0.5941268,"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."}}