{"id":"W4378213586","doi":"10.2196/preprints.45662","title":"Generate Analysis-Ready Data for Real-world Evidence: Tutorial for Harnessing Electronic Health Records With Advanced Informatic Technologies (Preprint)","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of British Columbia","funders":"","keywords":"Computer science; Leverage (statistics); Unstructured data; Data science; Big data; Data mining; Artificial intelligence","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.005187517,0.0006987205,0.001516948,0.001399329,0.0006396198,0.0009653633,0.006905817,0.0003676221,0.00000557268],"category_scores_gemma":[0.00199357,0.0005820186,0.0002468686,0.002454703,0.00009042643,0.001313176,0.00588238,0.00159903,0.00001319101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001127176,"about_ca_system_score_gemma":0.004897865,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.006701798,"about_ca_topic_score_gemma":0.02540931,"domain_scores_codex":[0.9933202,0.0002777619,0.001615793,0.002489874,0.0007399209,0.001556501],"domain_scores_gemma":[0.9884608,0.001713801,0.001814178,0.007177131,0.0006666066,0.0001675112],"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":[0.0005572203,0.00009801454,0.01075242,0.010269,0.001987339,0.000006179388,0.001446337,0.387173,0.00001251016,0.0739172,0.008462911,0.5053179],"study_design_scores_gemma":[0.0005565816,0.0006224274,0.001089455,0.001034877,0.0002091963,0.00000318762,0.0001628228,0.9774868,0.00005490491,0.01070931,0.007297331,0.0007731412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001882796,0.0005958919,0.9724708,0.01355089,0.002017632,0.005019657,0.0001798922,0.004199724,0.00008278099],"genre_scores_gemma":[0.08394046,0.00211956,0.903891,0.0004284574,0.0006540325,0.003925509,0.002696495,0.0001398799,0.002204663],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5903138,"threshold_uncertainty_score":0.9999127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1230525538215113,"score_gpt":0.4146534769718794,"score_spread":0.2916009231503682,"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."}}