{"id":"W4404764897","doi":"10.1186/s12911-024-02776-w","title":"Development and validation of a rheumatoid arthritis case definition: a machine learning approach using data from primary care electronic medical records","year":2024,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre; College of Physicians and Surgeons of Ontario; University of Alberta; Simon Fraser University; University of Calgary","funders":"Mitacs; Arthritis Society","keywords":"Random forest; Medicine; Machine learning; Artificial intelligence; Decision tree; Feature (linguistics); Medical record; Data mining; Cluster analysis; Computer science; Health informatics; Gradient boosting; Support vector machine; Cross-validation; Public health; Internal medicine; Pathology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001741454,0.0001665407,0.0004132829,0.0002302465,0.0002049592,0.0001529209,0.0001427539,0.000178466,0.0002620115],"category_scores_gemma":[0.0009755804,0.0001316118,0.00003942191,0.0002079163,0.0001481333,0.0003360142,0.0004646976,0.0005561668,0.000005777391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000652716,"about_ca_system_score_gemma":0.001433464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005348956,"about_ca_topic_score_gemma":0.000154048,"domain_scores_codex":[0.9970694,0.00008076557,0.000908543,0.0002396092,0.00141094,0.0002907056],"domain_scores_gemma":[0.9980979,0.001108709,0.0001148574,0.0002591809,0.00008636202,0.0003329827],"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":[0.0001519103,0.00003784293,0.00114804,0.0007866592,0.00007608342,0.0003409052,0.002482288,0.0000119141,0.000005856336,0.0004413199,0.00005468693,0.9944625],"study_design_scores_gemma":[0.002149329,0.0001228255,0.00007458674,0.01125274,0.000009289695,0.01114646,0.003579419,0.9637546,0.0000314861,0.0007941329,0.006888001,0.0001971068],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.656679,0.0434842,0.2991669,0.000009213542,0.00005477295,0.0001545481,0.00002566275,0.00004000115,0.0003856477],"genre_scores_gemma":[0.6424878,0.05159586,0.3051821,0.00007884722,0.00004265694,0.000008576964,0.0005852129,0.00001790008,0.000001077466],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9942654,"threshold_uncertainty_score":0.5366976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06798890512528732,"score_gpt":0.3331619303872496,"score_spread":0.2651730252619622,"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."}}