{"id":"W3046929991","doi":"10.2196/19848","title":"Chinese Clinical Named Entity Recognition in Electronic Medical Records: Development of a Lattice Long Short-Term Memory Model With Contextualized Character Representations","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Conditional random field; Artificial intelligence; Ambiguity; Deep learning; Interpretability; Chinese characters; Character (mathematics); Information retrieval","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":[0.001070632,0.0007788066,0.000770574,0.00111334,0.0004113327,0.000924867,0.00194678,0.0009961695,0.001779902],"category_scores_gemma":[0.003338205,0.0003290451,0.0009959514,0.001642657,0.0004281735,0.002716847,0.000958379,0.00149136,0.001036447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001049644,"about_ca_system_score_gemma":0.002241038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01736756,"about_ca_topic_score_gemma":0.01893829,"domain_scores_codex":[0.9994224,0.0001114422,0.00006598575,0.0002336414,0.0001024865,0.00006400329],"domain_scores_gemma":[0.9989769,0.00040945,0.000144376,0.0001353321,0.0002761621,0.00005780994],"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":[0.0003702651,0.000293208,0.00876626,0.0002946783,0.0002211136,0.0005307792,0.0003631577,0.2774159,0.007071679,0.01217563,0.01399851,0.6784987],"study_design_scores_gemma":[0.00001268735,0.00004556809,0.0006008372,0.00001936075,0.00003785643,0.00007135758,0.00003429565,0.9913523,0.001921384,0.004025403,0.001861317,0.00001772243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09577909,0.002740264,0.8868691,0.001862066,0.0003417647,0.0002596025,0.002840614,0.005601142,0.003706331],"genre_scores_gemma":[0.6851465,0.00216132,0.2980946,0.00100709,0.0002448188,0.0004577923,0.006679726,0.0001560745,0.006052122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01736756,"threshold_uncertainty_score":0.0345329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05722008833635078,"score_gpt":0.3631501154683155,"score_spread":0.3059300271319648,"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."}}