{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01016644,0.002677796,0.001343908,0.004337511,0.0006711393,0.004396893,0.003131275,0.002333516,0.05105011],"category_scores_gemma":[0.03943022,0.002187061,0.003238193,0.003090966,0.0008838426,0.006644542,0.004233559,0.004865683,0.03401839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001307215,"about_ca_system_score_gemma":0.00307576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002622694,"about_ca_topic_score_gemma":0.003450238,"domain_scores_codex":[0.9960634,0.001506518,0.0006549156,0.000453945,0.001220766,0.0001003819],"domain_scores_gemma":[0.9799785,0.01490766,0.0007778549,0.00145218,0.002271611,0.0006122327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002410101,0.0001909189,0.001304072,0.005489602,0.0002908036,0.0007858513,0.001076865,0.00978388,0.007397666,0.06630751,0.2309741,0.6761577],"study_design_scores_gemma":[0.0002094201,0.0001212693,0.00127587,0.002720938,0.0001109933,0.00118007,0.0002623009,0.05479718,0.007945311,0.1235873,0.80762,0.0001693801],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004213775,0.002505345,0.9678693,0.002461985,0.0004443667,0.001310186,0.004841017,0.01631846,0.00382786],"genre_scores_gemma":[0.002064378,0.002489632,0.9860089,0.0007826681,0.0001936181,0.0008287976,0.003071773,0.001773204,0.002786952],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05105011,"threshold_uncertainty_score":0.1707796,"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."}}