{"id":"W3094194910","doi":"10.2196/23930","title":"Machine Learning Electronic Health Record Identification of Patients with Rheumatoid Arthritis: Algorithm Pipeline Development and Validation Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Dutch Arthritis Association","keywords":"Computer science; Receiver operating characteristic; Artificial intelligence; Algorithm; Machine learning; Precision and recall; Identification (biology); Workflow; Data mining; F1 score; Medical diagnosis; Data set; Gold standard (test); Natural language processing; Medicine; Mathematics; Statistics; Database","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":[0.001007478,0.0001490427,0.0002969758,0.00009602929,0.000168583,0.00006789176,0.0003785777,0.00006074494,0.00001515703],"category_scores_gemma":[0.0002351036,0.0001256731,0.0000159516,0.0004107136,0.00003535954,0.0004283215,0.000201669,0.0005700968,0.00001224341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007309709,"about_ca_system_score_gemma":0.0004616525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003823473,"about_ca_topic_score_gemma":0.00002113648,"domain_scores_codex":[0.9970678,0.0001848016,0.001214058,0.0001838705,0.001053024,0.0002964215],"domain_scores_gemma":[0.9985054,0.00007829994,0.0007205522,0.0002069747,0.0001788775,0.000309899],"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":[0.00001295891,0.0001449809,0.07422185,0.0002007152,0.00001573232,8.096511e-7,0.02561114,0.00005947191,1.313609e-7,0.000186494,0.00005023391,0.8994955],"study_design_scores_gemma":[0.002381222,0.001754036,0.04388521,0.000228704,0.000002560681,0.000006857243,0.001334583,0.9433571,0.00004118727,0.00003894569,0.006702953,0.0002666083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4432185,0.0001510425,0.5542737,0.001326104,0.00005766028,0.0007976056,0.000002916534,0.0001555533,0.00001692555],"genre_scores_gemma":[0.9599264,0.000224833,0.03904602,0.0005995974,0.00002019697,0.00005118912,0.0001118846,0.00001241222,0.000007485935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9432977,"threshold_uncertainty_score":0.5124801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01205550059432132,"score_gpt":0.278860213071949,"score_spread":0.2668047124776277,"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."}}