{"id":"W3027889410","doi":"10.1038/s41467-020-16378-3","title":"Inferring multimodal latent topics from electronic health records","year":2020,"lang":"en","type":"article","venue":"Nature Communications","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Canada First Research Excellence Fund; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Government of Canada; J. Willard and Alice S. Marriott Foundation; Natural Sciences and Engineering Research Council of Canada; Mayo Clinic","keywords":"Health records; Leverage (statistics); Computer science; Electronic health record; Informatics; Diagnosis code; Data science; Health informatics; Machine learning; Data mining; Artificial intelligence; Medicine; Health care; Pathology; 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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0002089004,0.000118228,0.0001695474,0.00004512369,0.0003639074,0.00008102887,0.003065425,0.0001629939,0.00001840795],"category_scores_gemma":[0.000359642,0.0001219958,0.00005772628,0.0004199249,0.00002738807,0.0001805536,0.001092193,0.00243375,0.00003559262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001682477,"about_ca_system_score_gemma":0.0004130027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009935811,"about_ca_topic_score_gemma":0.001533692,"domain_scores_codex":[0.9985672,0.0003515646,0.0002727115,0.0003016868,0.000191817,0.0003149955],"domain_scores_gemma":[0.9972762,0.0002368458,0.0001421267,0.002036306,0.00007542775,0.000233127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001166132,0.0001747764,0.140687,0.00006380903,0.00008301192,0.000003289312,0.01156241,0.001054237,0.00009438884,0.5779535,0.01066539,0.2576466],"study_design_scores_gemma":[0.0002928259,0.0001393868,0.0722817,0.00003630085,0.000004529508,0.000002896701,0.00003345886,0.47627,0.00002665869,0.002864735,0.4478067,0.0002408312],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.008973774,0.02140097,0.06997087,0.8947176,0.0005930854,0.0005884092,0.00002542807,0.001112817,0.002617035],"genre_scores_gemma":[0.8800722,0.0006429919,0.1060625,0.01295523,0.0001375651,0.00001920711,0.00006092067,0.00001163003,0.00003767518],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.8817624,"threshold_uncertainty_score":0.9998677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03782611631966606,"score_gpt":0.3467720537823082,"score_spread":0.3089459374626422,"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."}}