{"id":"W4316174755","doi":"10.1177/14604582221115667","title":"Using ICD-9 diagnostic codes for external validation of topic models derived from primary care electronic medical record clinical text data","year":2023,"lang":"en","type":"article","venue":"Health Informatics Journal","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"North York General Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Diagnosis code; Topic model; Artificial intelligence; Face validity; Leverage (statistics); Natural language processing; Medicine; Population","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":[0.06995475,0.0009603446,0.0007264609,0.005291878,0.001153556,0.002829225,0.001697371,0.001151588,0.001501029],"category_scores_gemma":[0.2660034,0.0004916759,0.001827547,0.00386331,0.001508692,0.00210176,0.002513778,0.002111721,0.0009488188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0021804,"about_ca_system_score_gemma":0.002919327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008840969,"about_ca_topic_score_gemma":0.007869991,"domain_scores_codex":[0.9632338,0.02439952,0.003262441,0.005962186,0.00241121,0.0007307775],"domain_scores_gemma":[0.7271673,0.211726,0.0195723,0.02022903,0.01966872,0.001636576],"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":[0.0008330825,0.0003379808,0.9053835,0.0005538988,0.0008109726,0.0001678996,0.005429337,0.01732376,0.001694782,0.003161996,0.00497634,0.05932656],"study_design_scores_gemma":[0.0003768193,0.0007956058,0.5553439,0.0008031052,0.0006145603,0.0006236753,0.005150653,0.4004357,0.006068073,0.01636628,0.01321097,0.0002106762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8247467,0.0005018312,0.156365,0.0008120792,0.0002046877,0.001976555,0.01231524,0.0006275726,0.002450293],"genre_scores_gemma":[0.9210076,0.0001067968,0.05701358,0.0001398515,0.00007504379,0.001817439,0.0194079,0.0001163687,0.000315365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06995475,"threshold_uncertainty_score":0.3699605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2999121611428252,"score_gpt":0.5167997459878955,"score_spread":0.2168875848450703,"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."}}