{"id":"W4399772788","doi":"10.2196/60428","title":"Peer Review of “Performance Drift in Machine Learning Models for Cardiac Surgery Risk Prediction: Retrospective Analysis”","year":2024,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Retrospective cohort study; Medicine; Artificial intelligence; Computer science; Machine learning; Internal medicine","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":[0.003085693,0.0001529173,0.001508787,0.0003392771,0.00003701749,0.00001168911,0.00004236475,0.0000943769,0.00007776579],"category_scores_gemma":[0.001131214,0.0001158612,0.001341527,0.001144348,0.00003771848,0.0001129124,0.00001476577,0.0003322633,0.000006014136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009825134,"about_ca_system_score_gemma":0.00009077621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000429841,"about_ca_topic_score_gemma":0.000004836474,"domain_scores_codex":[0.9981332,0.0001533112,0.0005346254,0.0003001217,0.000665865,0.0002128716],"domain_scores_gemma":[0.9983618,0.0008745473,0.00009579647,0.0002403689,0.000338319,0.00008911823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000170456,0.00005070603,0.9788836,0.004609357,0.001576738,0.00003938114,0.0003466034,0.0005188568,0.00001718223,0.0006229862,0.006916211,0.00624792],"study_design_scores_gemma":[0.0004589272,0.0001517435,0.3929007,0.003604265,0.003869397,0.00001622493,0.00004946259,0.0684872,0.0001220611,0.00004650262,0.5300712,0.0002223292],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5215971,0.341795,0.007265755,0.04482283,0.002680276,0.007473946,0.0009250105,0.0009863963,0.07245369],"genre_scores_gemma":[0.9332707,0.0371213,0.0001671478,0.000148562,0.0002220023,0.0002046219,0.0003439641,0.00003078638,0.02849091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5859829,"threshold_uncertainty_score":0.4724681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02528289339510343,"score_gpt":0.2890196440600437,"score_spread":0.2637367506649402,"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."}}