{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01495573,0.00133467,0.001425421,0.002022278,0.0008327327,0.001537723,0.002239209,0.001774298,0.002296536],"category_scores_gemma":[0.02457645,0.0005136453,0.001477105,0.001579829,0.0005173856,0.001477051,0.001548317,0.001802751,0.001667209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001735513,"about_ca_system_score_gemma":0.004462029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01193207,"about_ca_topic_score_gemma":0.006295448,"domain_scores_codex":[0.9949188,0.002372227,0.0005841277,0.0009825808,0.0008108043,0.0003314536],"domain_scores_gemma":[0.9842101,0.01026668,0.000606966,0.001127629,0.00356047,0.0002280975],"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":[0.002251367,0.003532875,0.08943609,0.0007394056,0.0009018492,0.0003131694,0.0004297333,0.1514836,0.008428809,0.001060142,0.009556482,0.7318665],"study_design_scores_gemma":[0.0002724799,0.0006649867,0.008815531,0.00005207764,0.0001413681,0.0001546693,0.00007919859,0.9816315,0.0061959,0.000544119,0.00142596,0.00002230927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6437725,0.002074733,0.3338087,0.0009828784,0.0001740257,0.003147194,0.00293245,0.01086455,0.002243005],"genre_scores_gemma":[0.5374652,0.0004534436,0.4487318,0.0002910076,0.00005256339,0.00198759,0.008892217,0.0002243247,0.001901967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01495573,"threshold_uncertainty_score":0.07909441,"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."}}