{"id":"W2798075524","doi":"10.1016/j.jbi.2018.04.008","title":"Co-occurrence of medical conditions: Exposing patterns through probabilistic topic modeling of snomed codes","year":2018,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Institute of General Medical Sciences","keywords":"Optimal distinctiveness theory; SNOMED CT; Probabilistic logic; Computer science; Topic model; Diagnosis code; Disease; Population; Data science; Natural language processing; Medicine; Artificial intelligence; Psychology; Terminology; Pathology; Linguistics; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"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":[0.004796737,0.0009848498,0.0007766707,0.007265158,0.0008002018,0.002141285,0.001096295,0.001420427,0.001137691],"category_scores_gemma":[0.02029667,0.0004431093,0.002291808,0.005977805,0.0009530199,0.00315656,0.001834673,0.001581941,0.0005801666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008971709,"about_ca_system_score_gemma":0.001400122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00981104,"about_ca_topic_score_gemma":0.01338932,"domain_scores_codex":[0.9962059,0.001420534,0.0003659313,0.001184003,0.0005878738,0.0002357235],"domain_scores_gemma":[0.9751229,0.01990234,0.002264254,0.001319282,0.001024188,0.0003669253],"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":[0.001573645,0.0006555757,0.5959988,0.002595375,0.001443045,0.002532304,0.01098046,0.09653202,0.01491852,0.02655179,0.01847488,0.2277435],"study_design_scores_gemma":[0.0001100852,0.0002847791,0.1337834,0.0003794657,0.0006626329,0.003469737,0.002211072,0.7850608,0.003974199,0.04679298,0.02309557,0.0001753257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5388424,0.007404639,0.4268915,0.002554973,0.0002937977,0.000664136,0.01693184,0.001907509,0.004509157],"genre_scores_gemma":[0.8822346,0.001866848,0.09834316,0.0003506608,0.0003688482,0.0005017091,0.01507546,0.0001593265,0.001099338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00981104,"threshold_uncertainty_score":0.02536792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05031887622129858,"score_gpt":0.3761497957929399,"score_spread":0.3258309195716413,"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."}}