{"id":"W4212950717","doi":"10.2196/29290","title":"A Traditional Chinese Medicine Syndrome Classification Model Based on Cross-Feature Generation by Convolution Neural Network: Model Development and Validation","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Traditional Chinese Medicine Studies","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; Health Commission of Sichuan Province","keywords":"Computer science; Artificial intelligence; Medical record; Traditional Chinese medicine; Medical prescription; Convolutional neural network; Artificial neural network; Feature (linguistics); Dialectic; Machine learning; Medicine; Data mining; Alternative medicine; Pathology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008448019,0.0003270333,0.0004526812,0.0002219282,0.0006841358,0.0000255193,0.0001433787,0.0001616378,0.0001914278],"category_scores_gemma":[0.0002684275,0.0002490949,0.0000645306,0.0003910791,0.0003132831,0.0002816104,0.00006540898,0.0008274406,0.000005451371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003792554,"about_ca_system_score_gemma":0.0004732799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001759771,"about_ca_topic_score_gemma":0.000001449595,"domain_scores_codex":[0.9960067,0.00007024896,0.0008757791,0.0002573119,0.002457867,0.0003320896],"domain_scores_gemma":[0.9987351,0.0001917723,0.0002928133,0.0002346278,0.0001690651,0.0003766287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008945939,0.001292887,0.01083768,0.0009116775,0.0002316499,0.00005695201,0.007970044,0.6437135,0.0006276777,0.009081576,0.3176292,0.006752546],"study_design_scores_gemma":[0.003316973,0.0004850778,0.02736191,0.0001077883,0.00004814415,0.0002636831,0.0001721606,0.966756,0.000007439494,0.0005062745,0.0007579416,0.0002165676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9425767,0.000146927,0.04208454,0.01222787,0.000348053,0.0009503803,0.0001309349,0.0001629563,0.001371615],"genre_scores_gemma":[0.9786562,0.00001724771,0.005511317,0.00727293,0.0004600372,0.0006089677,0.007199632,0.00002855283,0.0002450591],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3230425,"threshold_uncertainty_score":0.9999961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05990583311459774,"score_gpt":0.3155221708259527,"score_spread":0.255616337711355,"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."}}