{"id":"W4307385604","doi":"10.1038/s41598-022-22956-w","title":"Modeling electronic health record data using an end-to-end knowledge-graph-informed topic model","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research","keywords":"Computer science; End-to-end principle; Graph; Data science; Knowledge graph; End user; Data mining; Information retrieval; World Wide Web; Theoretical computer science; Artificial intelligence","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.006925054,0.000253373,0.0003504592,0.0006941482,0.002444473,0.0006576186,0.002697503,0.00004942696,0.0000861357],"category_scores_gemma":[0.0002252364,0.0002745633,0.00008211002,0.002100589,0.00005872978,0.001249117,0.003034245,0.0007423021,0.000009622403],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008353769,"about_ca_system_score_gemma":0.006080559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001643335,"about_ca_topic_score_gemma":0.001748461,"domain_scores_codex":[0.9939497,0.0003766107,0.001045304,0.002212837,0.00116997,0.001245619],"domain_scores_gemma":[0.9934129,0.00004692444,0.0004218361,0.005404893,0.0002058704,0.0005076306],"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":[0.000005070831,0.000115934,0.0007962327,0.00006947541,0.00001061553,0.00005379544,0.003862673,0.9203505,0.0001562959,0.002092603,0.002145643,0.07034118],"study_design_scores_gemma":[0.00007254529,0.0001182513,0.0000225226,0.00002241451,0.000004281803,0.000279907,0.0001177746,0.9685643,0.00001629991,0.01093938,0.0195713,0.0002709827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2978266,0.0005992042,0.6890939,0.001530502,0.009111392,0.0008111085,0.00001388884,0.0004566299,0.0005566973],"genre_scores_gemma":[0.9282044,0.000006732816,0.06986909,0.0004309728,0.0001092911,0.00004590003,0.0002195826,0.00003211003,0.001081993],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6303777,"threshold_uncertainty_score":0.9999707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1018581186794975,"score_gpt":0.3765843468933598,"score_spread":0.2747262282138623,"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."}}