{"id":"W4378172411","doi":"10.2196/45662","title":"Generate Analysis-Ready Data for Real-world Evidence: Tutorial for Harnessing Electronic Health Records With Advanced Informatic Technologies","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of British Columbia","funders":"U.S. National Library of Medicine; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Neurological Disorders and Stroke; National Institutes of Health","keywords":"Computer science; Leverage (statistics); Data science; Missing data; Data mining; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.02787923,0.0001699683,0.0006503632,0.001840104,0.0002504583,0.0004171214,0.005593047,0.0001583579,0.00001887835],"category_scores_gemma":[0.01176943,0.0001153645,0.000117863,0.003670416,0.0001796023,0.001115808,0.001204289,0.002024368,0.000007759432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005693448,"about_ca_system_score_gemma":0.004327598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009348832,"about_ca_topic_score_gemma":0.002845476,"domain_scores_codex":[0.9935944,0.0005919149,0.001167404,0.0004648275,0.003011898,0.001169534],"domain_scores_gemma":[0.9926944,0.003923147,0.0007020333,0.001132474,0.001202224,0.0003457341],"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":[0.001093439,0.0001078037,0.004898997,0.001464829,0.0008117895,0.00008997576,0.001508279,0.001783936,0.00002417176,0.02152914,0.1055626,0.8611251],"study_design_scores_gemma":[0.001049079,0.003292399,0.0006782372,0.001324111,0.00003865927,0.00004901675,0.000388139,0.9358439,0.0000702193,0.002061807,0.05504415,0.0001603168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04474765,0.001965144,0.8185171,0.1313172,0.001591002,0.001395826,0.00002360502,0.0003796034,0.0000628511],"genre_scores_gemma":[0.8826243,0.007311118,0.1041077,0.0005984382,0.00232077,0.0002957643,0.0001800164,0.00007314741,0.00248876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9340599,"threshold_uncertainty_score":0.9997872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1995632703362615,"score_gpt":0.5260047112488783,"score_spread":0.3264414409126167,"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."}}