{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001656335,0.0001245048,0.0004519283,0.0002302784,0.00008177123,0.00004012246,0.001252161,0.0001677787,0.0001017245],"category_scores_gemma":[0.001645822,0.00009434643,0.0001044814,0.0003723391,0.0004598075,0.0006143613,0.000160185,0.0005181427,0.000004280437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005670284,"about_ca_system_score_gemma":0.0006284272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003349058,"about_ca_topic_score_gemma":0.000003102509,"domain_scores_codex":[0.9957298,0.0001040368,0.002057117,0.00007898678,0.001780805,0.0002492492],"domain_scores_gemma":[0.9970727,0.000441036,0.001254116,0.0003143878,0.0006604132,0.0002573311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003461089,0.00484361,0.05550989,0.03620204,0.001362412,0.0003358795,0.3454878,0.02036316,0.001213654,0.1921801,0.02074579,0.3214096],"study_design_scores_gemma":[0.0006491004,0.0009744323,0.0004471497,0.001630099,0.00001933025,0.0002545641,0.0007826783,0.9904388,0.0002842199,0.003590054,0.000800666,0.0001289164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2422898,0.00005993115,0.7555033,0.00133794,0.0005398446,0.00009533747,0.00003256625,0.00001632339,0.0001249853],"genre_scores_gemma":[0.9507012,0.00008416444,0.04864129,0.0003683413,0.0001862367,0.000001589043,0.00001214799,0.000003769163,0.000001203245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9700756,"threshold_uncertainty_score":0.3847336,"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."}}