{"id":"W2611354752","doi":"10.5210/ojphi.v9i1.7648","title":"Automated Classification of Alcohol Use by Text Mining of Electronic Medical Records","year":2017,"lang":"en","type":"article","venue":"Online Journal of Public Health Informatics","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; George & Fay Yee Centre for Healthcare Innovation","funders":"Mitacs","keywords":"Medical record; Computer science; Medicine; Health records; Health care; Unstructured data; Primary care; Disease; Data science; Information retrieval; Family medicine; Artificial intelligence; Data mining; Big data; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.002387968,0.0001319589,0.0006867506,0.0002830646,0.0001003056,0.00003306322,0.0003048313,0.0001389717,0.00007856445],"category_scores_gemma":[0.003051743,0.00009477888,0.0001301296,0.0001609637,0.000119313,0.000886548,0.000027832,0.0003403856,0.000002167705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002603209,"about_ca_system_score_gemma":0.003087047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001982294,"about_ca_topic_score_gemma":0.00005627305,"domain_scores_codex":[0.9963997,0.00006496609,0.002258474,0.00004845942,0.0008561378,0.0003722835],"domain_scores_gemma":[0.9941157,0.0002025251,0.004214628,0.0003918524,0.0006615063,0.0004138573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001894646,0.001186603,0.7770654,0.0006099261,0.0005390373,0.000009069437,0.006089293,0.000003172234,0.0001013469,0.0003936887,0.03480401,0.179009],"study_design_scores_gemma":[0.0146915,0.003381981,0.8632093,0.002074793,0.0002112657,0.0005284154,0.007450746,0.05882555,0.0002753809,0.00003594664,0.04905596,0.0002591694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9875748,0.0003165532,0.0005277276,0.01093955,0.0001816001,0.0001647242,0.00001336993,0.00002646061,0.0002551808],"genre_scores_gemma":[0.9875171,0.002208967,0.00927339,0.0006649816,0.00009476469,0.000001194338,0.0000738451,0.00001396808,0.0001517725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1787498,"threshold_uncertainty_score":0.5476288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1334890589865161,"score_gpt":0.4127568772933147,"score_spread":0.2792678183067986,"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."}}