{"id":"W4294052933","doi":"10.1016/j.jbi.2022.104190","title":"MixEHR-Guided: A guided multi-modal topic modeling approach for large-scale automatic phenotyping using the electronic health record","year":2022,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Machine learning; Artificial intelligence; Health informatics; Data mining; Inference; Population; Data science; Medicine; Public health","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005630881,0.0001923267,0.000484209,0.0003252478,0.00110775,0.0001424172,0.001610822,0.0000789902,0.00001740941],"category_scores_gemma":[0.0003409006,0.0001393768,0.0002266067,0.0006833517,0.00003958485,0.000456376,0.0005431855,0.001253973,9.485657e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009660012,"about_ca_system_score_gemma":0.001467294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001078035,"about_ca_topic_score_gemma":0.000005383868,"domain_scores_codex":[0.9955789,0.0003423007,0.002073913,0.0001408443,0.001053008,0.0008110701],"domain_scores_gemma":[0.9974196,0.0002148035,0.001401142,0.0004543077,0.0002319315,0.0002782223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005161535,0.0009489235,0.0006865159,0.002880131,0.0003092605,0.00001067534,0.07404564,0.6720851,0.00004556493,0.0121598,0.007472983,0.2293038],"study_design_scores_gemma":[0.0009889948,0.0003669532,0.00001299368,0.00006673159,0.00001563528,0.000511457,0.002370806,0.9858599,0.000001364018,0.0007090768,0.00895378,0.0001422848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04225434,0.0003394669,0.9518939,0.004262102,0.0006903844,0.0004739433,0.0000077419,0.00006058182,0.00001753199],"genre_scores_gemma":[0.1749906,0.00002925264,0.8210585,0.003562958,0.0002778026,0.0000261445,0.00001240176,0.00002027304,0.00002202663],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3137748,"threshold_uncertainty_score":0.8520033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06237262631338839,"score_gpt":0.3547260243753848,"score_spread":0.2923533980619964,"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."}}