{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009243781,0.0008080289,0.0009641355,0.001069776,0.0005356948,0.0006448298,0.001676832,0.001241051,0.002453337],"category_scores_gemma":[0.001656412,0.0003383687,0.001250779,0.000898007,0.000393506,0.001993806,0.001087974,0.000966542,0.001546866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004153623,"about_ca_system_score_gemma":0.0009176405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002870372,"about_ca_topic_score_gemma":0.003259997,"domain_scores_codex":[0.999057,0.0001022657,0.00009240426,0.0004841286,0.0001930149,0.00007113905],"domain_scores_gemma":[0.9993708,0.0001272419,0.00007640541,0.0001253271,0.000239022,0.0000613734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003648396,0.0004219818,0.005799592,0.00022139,0.0001575084,0.0005720811,0.0001864707,0.03419573,0.06628765,0.002603648,0.007142164,0.8820469],"study_design_scores_gemma":[0.00002313061,0.0001407457,0.0028253,0.00001210041,0.00006767326,0.0003967494,0.0000586647,0.9640011,0.02713512,0.001483032,0.003819632,0.00003681778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03158938,0.0003708642,0.9618639,0.0002553153,0.00008257046,0.0002568745,0.0002892111,0.003885977,0.001405991],"genre_scores_gemma":[0.3171674,0.0003049489,0.6724243,0.0003929675,0.0001032378,0.0003448221,0.003106814,0.0001755309,0.005980114],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002870372,"threshold_uncertainty_score":0.008207202,"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."}}