{"id":"W2801562942","doi":"10.1016/j.cmpb.2018.05.008","title":"Deep generative learning for automated EHR diagnosis of traditional Chinese medicine","year":2018,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Traditional Chinese Medicine Studies","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Deep belief network; Artificial intelligence; Machine learning; Decision tree; Deep learning; Support vector machine; Set (abstract data type); Supervised learning; Data set; Feature engineering; Feature learning; Data mining; Artificial neural network","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":[0.00153629,0.0003303462,0.001058141,0.0005204557,0.0001374799,0.000007324509,0.0001088184,0.0001143492,0.00006193476],"category_scores_gemma":[0.0008013909,0.0002102363,0.00009448755,0.0009557079,0.001623429,0.00006524703,0.00006073736,0.0002524971,8.673863e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004441131,"about_ca_system_score_gemma":0.00004622952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004298634,"about_ca_topic_score_gemma":0.00001380861,"domain_scores_codex":[0.9978411,0.0002380143,0.0007462056,0.0004845645,0.0003592525,0.000330888],"domain_scores_gemma":[0.9972606,0.001713834,0.0002054128,0.0001893823,0.000423524,0.0002072259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005883593,0.0008130052,0.236769,0.0009879649,0.0004988535,0.00004116169,0.0071576,0.0000156381,0.002725877,0.001576986,0.003097154,0.7457284],"study_design_scores_gemma":[0.01361365,0.02299271,0.6913065,0.002185066,0.0003785102,0.0003642638,0.000513591,0.2457612,0.0003983856,0.009435603,0.01261085,0.0004396729],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4120824,0.006769927,0.5625204,0.01295565,0.002132989,0.002434814,0.0000156849,0.0004761168,0.0006120538],"genre_scores_gemma":[0.4628105,0.0002391319,0.5317931,0.0006352197,0.003913146,0.0002632268,0.0002889022,0.00003075247,0.00002594891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7452887,"threshold_uncertainty_score":0.8573189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.109293911228475,"score_gpt":0.4163887865333212,"score_spread":0.3070948753048462,"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."}}