{"id":"W3014193862","doi":"10.23889/ijpds.v5i1.1156","title":"The effect of number of healthcare visits on study sample selection in electronic health record data","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada)","funders":"National Center for Advancing Translational Sciences; National Center for Chronic Disease Prevention and Health Promotion","keywords":"Medicine; Sample (material); Health care; Electronic health record; Sample size determination; Family medicine; Gerontology; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.01018331,0.00008152192,0.0002160579,0.000148313,0.0008444205,0.00002851933,0.001763825,0.00004121251,0.00003067643],"category_scores_gemma":[0.00732583,0.00005587209,0.00001957638,0.0005015239,0.00004074304,0.0009271632,0.0003192218,0.0005859801,0.000007343183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003890159,"about_ca_system_score_gemma":0.001051338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003373752,"about_ca_topic_score_gemma":0.002772216,"domain_scores_codex":[0.9965693,0.0005112574,0.001231603,0.0002677556,0.001061474,0.0003586129],"domain_scores_gemma":[0.9965076,0.001454642,0.001122728,0.0003427824,0.0004068674,0.0001653576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001005288,0.00005262158,0.899156,0.0001705897,0.00001786534,2.053021e-7,0.001070676,0.0001739037,0.00001279594,0.00441708,0.003337139,0.09058579],"study_design_scores_gemma":[0.005183277,0.005357985,0.6301221,0.0009640862,0.00002104988,0.00001085065,0.002387609,0.3095788,0.00002783972,0.001688606,0.04443538,0.0002223877],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9423104,0.00006542881,0.01325637,0.03860835,0.002425705,0.002376664,0.0008410643,0.00002981518,0.0000862001],"genre_scores_gemma":[0.9978133,0.0001224974,0.0005504941,0.0007960912,0.000314883,0.0000146059,0.0003738558,0.000006186556,0.000008085451],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3094049,"threshold_uncertainty_score":0.8770232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.338917648568192,"score_gpt":0.5860153991181046,"score_spread":0.2470977505499126,"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."}}