{"id":"W3171691821","doi":"10.2196/28219","title":"Extraction of Traditional Chinese Medicine Entity: Design of a Novel Span-Level Named Entity Recognition Method With Distant Supervision","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Traditional Chinese Medicine Studies","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China","keywords":"Computer science; Artificial intelligence; Medical diagnosis; Classifier (UML); F1 score; Gold standard (test); Supervised learning; Medical record; Natural language processing; Named-entity recognition; Set (abstract data type); Machine learning; Data mining; Pattern recognition (psychology); Artificial neural network; Medicine; Task (project management)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001187074,0.0003126457,0.00101177,0.000310362,0.00008985923,0.000007658393,0.0001402559,0.0002034849,0.001214743],"category_scores_gemma":[0.002762836,0.0002025455,0.0001483761,0.0008727943,0.0005635389,0.0003890473,0.00005703199,0.0005712451,0.000007273668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001040299,"about_ca_system_score_gemma":0.0006614118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004055429,"about_ca_topic_score_gemma":0.00002606491,"domain_scores_codex":[0.9952508,0.0001157306,0.001467347,0.0002128234,0.002687012,0.0002662825],"domain_scores_gemma":[0.9963432,0.001389434,0.0005255454,0.0003355703,0.001041446,0.0003648061],"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":[0.02479826,0.06722146,0.07952944,0.07375054,0.01324171,0.003101194,0.1247673,0.001059276,0.2439025,0.02337555,0.06449751,0.2807553],"study_design_scores_gemma":[0.07655805,0.01273723,0.64144,0.02726997,0.003383183,0.016512,0.02384926,0.1610716,0.01829464,0.01364508,0.003198436,0.00204059],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4212157,0.0001754436,0.572968,0.002462849,0.0004213425,0.0007444178,0.0002560796,0.00006446846,0.001691686],"genre_scores_gemma":[0.8340421,0.0003357509,0.1623938,0.0007357775,0.0006227691,0.0001004282,0.001652612,0.00003456098,0.00008223148],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5619106,"threshold_uncertainty_score":0.9996983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1207667727668034,"score_gpt":0.3652771490616177,"score_spread":0.2445103762948144,"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."}}