{"id":"W4293575108","doi":"10.2196/39057","title":"Standard Vocabularies to Improve Machine Learning Model Transferability With Electronic Health Record Data: Retrospective Cohort Study Using Health Care–Associated Infection","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; Agency for Healthcare Research and Quality; National Institutes of Health","keywords":"Health records; Electronic health record; Health care; Retrospective cohort study; Transferability; Computer science; Health data; Medicine; Cohort; Artificial intelligence; Data science; Machine learning; Surgery","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006583026,0.0003432137,0.0008853753,0.000252091,0.001753692,0.0001846344,0.001270767,0.0001006781,0.00003504552],"category_scores_gemma":[0.0004956886,0.0003143195,0.00005916291,0.001343199,0.00007255083,0.0008083069,0.001148225,0.003272403,0.000002188428],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.005955775,"about_ca_system_score_gemma":0.005899291,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007417688,"about_ca_topic_score_gemma":0.007140262,"domain_scores_codex":[0.9928938,0.001211778,0.001309374,0.0006417962,0.002874449,0.001068865],"domain_scores_gemma":[0.9970598,0.0001282991,0.0006214994,0.001246271,0.0003125557,0.0006316097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002760054,0.0005495563,0.7540717,0.0005586065,0.0002084488,0.0000081672,0.1350688,0.05496185,5.310238e-7,0.0009473139,0.000374656,0.05297441],"study_design_scores_gemma":[0.00113627,0.008451049,0.02286801,0.0000547669,0.00001389282,0.00002015365,0.002419189,0.9635297,5.860412e-7,0.0001080764,0.001078505,0.0003197701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5203164,0.00006475425,0.4733699,0.002432272,0.0002530535,0.002944416,0.0001203178,0.000460609,0.00003834396],"genre_scores_gemma":[0.983122,0.00003398158,0.01383394,0.002375313,0.00004995752,0.0002708793,0.0002611012,0.00003640015,0.00001641994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9085679,"threshold_uncertainty_score":0.9999309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01967308320530024,"score_gpt":0.3361374169679677,"score_spread":0.3164643337626675,"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."}}