{"id":"W3210677193","doi":"10.1186/s12911-021-01669-6","title":"Assessing the suitability of general practice electronic health records for clinical prediction model development: a data quality assessment","year":2021,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"National Health and Medical Research Council; RACGP Foundation; Medical Research Council; Royal Australian College of General Practitioners; Australian Orthopaedic Association","keywords":"Medicine; Health informatics; Health records; Data quality; Gold standard (test); Medical record; Family medicine; Health care; Public health; Surgery; Operations management; Internal medicine","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02948786,0.0001286541,0.0003816109,0.00005017117,0.0004256141,0.0003137321,0.0009820126,0.0001380586,0.000006832851],"category_scores_gemma":[0.01397757,0.00009104115,0.00006062632,0.0002696158,0.00006680001,0.001181968,0.00143371,0.0006389468,5.34535e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001278722,"about_ca_system_score_gemma":0.008032002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002002512,"about_ca_topic_score_gemma":0.0001260052,"domain_scores_codex":[0.9947412,0.0008317626,0.00233979,0.0003592091,0.001345426,0.0003825928],"domain_scores_gemma":[0.9846231,0.01241935,0.001027614,0.0012596,0.0004643703,0.0002059829],"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":[0.00001956133,0.00009217259,0.009317981,0.0003953025,0.00001741128,4.380751e-7,0.0006229811,0.001666441,1.383998e-7,0.01709962,0.000541625,0.9702263],"study_design_scores_gemma":[0.0004333356,0.0000663497,0.01316744,0.0002416061,0.000006838565,0.00002862633,0.0004715119,0.9766726,5.740646e-7,0.005552333,0.003274245,0.00008450149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04545812,0.0003690916,0.952383,0.0009287958,0.0003307204,0.0002958593,0.0000105278,0.00003937653,0.0001844531],"genre_scores_gemma":[0.1016569,0.000283909,0.8959072,0.002013096,0.00007410945,0.00001439741,0.00004003728,0.000005887201,0.000004416907],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9750062,"threshold_uncertainty_score":0.9993465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2872856093899279,"score_gpt":0.5629759558264738,"score_spread":0.2756903464365458,"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."}}