{"id":"W4387950762","doi":"10.2196/50895","title":"Temporal Generalizability of Machine Learning Models for Predicting Postoperative Delirium Using Electronic Health Record Data: Model Development and Validation Study","year":2023,"lang":"en","type":"article","venue":"JMIR Perioperative Medicine","topic":"Intensive Care Unit Cognitive Disorders","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Ministry of Health, Labour and Welfare","keywords":"Generalizability theory; Brier score; Receiver operating characteristic; Delirium; Logistic regression; Medicine; Artificial intelligence; Statistics; Machine learning; Decision tree; Computer science; Mathematics; Intensive care medicine","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"],"consensus_categories":[],"category_scores_codex":[0.00179744,0.0003594739,0.0009185519,0.0003704681,0.0004574904,0.00001686328,0.0001377694,0.00007806053,0.00001427705],"category_scores_gemma":[0.002688901,0.0002866622,0.00004625902,0.0005406923,0.0002457293,0.0003201123,0.0001917251,0.0004227769,7.545099e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000344946,"about_ca_system_score_gemma":0.001030256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005117683,"about_ca_topic_score_gemma":0.0003435169,"domain_scores_codex":[0.9970339,0.0003460749,0.0008632228,0.0007925981,0.0004496961,0.0005145302],"domain_scores_gemma":[0.9934966,0.0001711022,0.0002811229,0.0003621512,0.005525698,0.0001633449],"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":[0.006416167,0.002036894,0.4554513,0.002672115,0.002405785,0.00005576062,0.3510139,0.07072949,0.06212137,0.001090566,0.003025565,0.04298112],"study_design_scores_gemma":[0.004841028,0.003649753,0.002102467,0.0003405872,0.0001160585,0.00001581045,0.04953627,0.9379029,0.0009015238,0.00005168487,0.0002995427,0.0002423592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9171973,0.000385695,0.07472273,0.003181076,0.00009844446,0.004171919,0.00008626513,0.0001018717,0.00005469945],"genre_scores_gemma":[0.9876929,0.0000869099,0.006765767,0.002441115,0.000095434,0.0002648873,0.002305284,0.00006559843,0.000282098],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8671734,"threshold_uncertainty_score":0.9999586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1325988442796283,"score_gpt":0.3903482400034451,"score_spread":0.2577493957238168,"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."}}