{"id":"W4396636615","doi":"10.2196/50437","title":"Considerations for Quality Control Monitoring of Machine Learning Models in Clinical Practice","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering","keywords":"Quality (philosophy); Computer science; Control (management); Medicine; Machine learning; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005933246,0.0001198803,0.000354153,0.0001448166,0.00008383246,0.0001218507,0.0003711985,0.000208406,0.0000153051],"category_scores_gemma":[0.01322482,0.0001039083,0.0001066026,0.0002766155,0.00007539218,0.001081383,0.0001368743,0.001226309,0.00001049085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005215405,"about_ca_system_score_gemma":0.000564745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008263464,"about_ca_topic_score_gemma":0.00001048581,"domain_scores_codex":[0.996519,0.0004456345,0.001845052,0.0001579999,0.0007629441,0.0002693273],"domain_scores_gemma":[0.9864638,0.01247467,0.0003072977,0.0003122502,0.0002336615,0.0002083474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007310391,0.0003346421,0.02871152,0.003622371,0.0001312987,0.00006044264,0.03141766,0.02360324,0.00000371991,0.6931766,0.001128553,0.2177368],"study_design_scores_gemma":[0.0006370044,0.0001376036,0.001059494,0.0002919585,0.000006685747,0.00002675031,0.0003884831,0.9871244,0.00000388801,0.005997135,0.004223286,0.0001032421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01659502,0.0004749253,0.9706498,0.00876385,0.001044613,0.0006722684,0.00001068692,0.0002750357,0.001513802],"genre_scores_gemma":[0.8184516,0.00006137545,0.1804337,0.0007834015,0.0001514646,0.00008233505,0.000004129476,0.000008591023,0.00002345985],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9635212,"threshold_uncertainty_score":0.9950872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1212489166717202,"score_gpt":0.4716219799815563,"score_spread":0.3503730633098361,"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."}}