{"id":"W4200297453","doi":"10.1101/2021.12.17.473215","title":"MixEHR-Guided: A guided multi-modal topic modeling approach for large-scale automatic phenotyping using the electronic health record","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Machine learning; Artificial intelligence; Health informatics; Inference; Data mining; Health care","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004357108,0.001201848,0.001345019,0.001583684,0.0006909015,0.001246079,0.00258652,0.001707214,0.00245874],"category_scores_gemma":[0.00723084,0.0009211461,0.002440828,0.001109197,0.0007431977,0.001304654,0.002381299,0.002340462,0.001217664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001097074,"about_ca_system_score_gemma":0.00123958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01178744,"about_ca_topic_score_gemma":0.0174115,"domain_scores_codex":[0.9981951,0.0009163442,0.00007672368,0.0005413141,0.0001574744,0.0001131207],"domain_scores_gemma":[0.9944198,0.004516734,0.0002573382,0.0003928822,0.000272402,0.0001408159],"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":[0.000553283,0.0003473376,0.01297864,0.0002801458,0.0004467723,0.0004995688,0.001084569,0.6498966,0.006596099,0.02130189,0.01361493,0.2924001],"study_design_scores_gemma":[0.00002149504,0.00001732381,0.0003733524,0.00000931574,0.00001574907,0.00003152664,0.00002572916,0.9900119,0.0003718694,0.008439793,0.000670146,0.00001195225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02373186,0.0004309131,0.9704516,0.0006478873,0.00003272153,0.0001201955,0.0007879004,0.003322616,0.0004742275],"genre_scores_gemma":[0.4822491,0.0004125534,0.5058262,0.001008609,0.000253726,0.0006653155,0.00503496,0.000806748,0.003742614],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01178744,"threshold_uncertainty_score":0.02343768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04947228149419877,"score_gpt":0.3040285454588539,"score_spread":0.2545562639646551,"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."}}