{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05471797,0.0008023229,0.0009038041,0.003172511,0.001100661,0.002195809,0.002165963,0.001074992,0.001988126],"category_scores_gemma":[0.160217,0.0004332351,0.003330163,0.00281649,0.001035389,0.002868817,0.002536174,0.001784824,0.0003952885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001497232,"about_ca_system_score_gemma":0.002062464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007415744,"about_ca_topic_score_gemma":0.005379389,"domain_scores_codex":[0.9714178,0.013604,0.007031975,0.004257814,0.003003302,0.0006850611],"domain_scores_gemma":[0.8915155,0.05885921,0.01959122,0.01962873,0.009245236,0.001160111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001475779,0.0003390989,0.9651847,0.0003311495,0.002087181,0.0001891508,0.001524597,0.004644935,0.0007474806,0.000621928,0.001571313,0.02128249],"study_design_scores_gemma":[0.0006229223,0.003230358,0.9059947,0.0007184487,0.002787684,0.0008699865,0.003415765,0.06691895,0.003704624,0.004186417,0.007317299,0.0002328572],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9783152,0.0007174252,0.01614474,0.0002191636,0.00007046847,0.0006854058,0.003241479,0.00008729807,0.0005188644],"genre_scores_gemma":[0.9870717,0.0001160774,0.007194324,0.00007340723,0.00003292525,0.0008792887,0.004457353,0.00005038911,0.0001245068],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05471797,"threshold_uncertainty_score":0.2893798,"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."}}