{"id":"W4410850908","doi":"10.1177/0272989x251343082","title":"So You’ve Got a High AUC, Now What? An Overview of Important Considerations when Bringing Machine-Learning Models from Computer to Bedside","year":2025,"lang":"en","type":"review","venue":"Medical Decision Making","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Public Health Ontario; University of Toronto","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Bridge (graph theory); Software deployment; Key (lock); Model selection; Clinical decision support system; Health care; Clinical Practice; Calibration; Medical physics; Decision support system; Medicine; Software engineering","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":[],"category_scores_codex":[0.00434332,0.001120841,0.00215176,0.004002084,0.0003001816,0.001714307,0.001397501,0.001725273,0.005343395],"category_scores_gemma":[0.01080517,0.0004915848,0.002378141,0.002862201,0.0004998792,0.002255472,0.0006479424,0.002815529,0.002750852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001101315,"about_ca_system_score_gemma":0.002182096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00250408,"about_ca_topic_score_gemma":0.004501287,"domain_scores_codex":[0.998183,0.0006889603,0.0003920104,0.0001897429,0.0004772452,0.00006909463],"domain_scores_gemma":[0.99508,0.003653848,0.000398939,0.00007168262,0.0007082378,0.0000871868],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009516326,0.00003693565,0.0003301656,0.03504683,0.0005611199,0.00009161078,0.0000706563,0.000662507,0.0005015909,0.004686629,0.05347074,0.9044461],"study_design_scores_gemma":[0.00007232986,0.0002479849,0.001900682,0.04444453,0.001234075,0.0012123,0.0000966119,0.0007081701,0.0009188566,0.009966876,0.9391127,0.00008491427],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00009748107,0.995824,0.0006591121,0.001860163,0.0002727177,0.00002573949,0.00009902354,0.00002331894,0.001138516],"genre_scores_gemma":[0.001750402,0.9937398,0.0019949,0.00133501,0.0003206849,0.00006934821,0.0001447062,0.00001462613,0.0006305284],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9956567,"threshold_uncertainty_score":0.0229699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3326424958883833,"score_gpt":0.5007955916939023,"score_spread":0.168153095805519,"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."}}