{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001627105,0.0001957277,0.0005009972,0.0001164398,0.00005762513,0.00004850332,0.0009089576,0.0002670618,0.0001397034],"category_scores_gemma":[0.001022304,0.0001525885,0.00008441888,0.0004535253,0.0001342178,0.0008434113,0.0003708405,0.0008960419,0.00003107316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008015075,"about_ca_system_score_gemma":0.001731674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009544582,"about_ca_topic_score_gemma":0.0002626588,"domain_scores_codex":[0.9956507,0.0001495052,0.001964298,0.0002745272,0.001556758,0.0004041958],"domain_scores_gemma":[0.9982539,0.000330494,0.0003187601,0.0003959705,0.0001630523,0.0005378076],"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":[0.0004139511,0.001285753,0.06157657,0.0009892051,0.0002727211,0.0001386003,0.09368284,0.0002642885,0.00002050272,0.001402072,0.0004689376,0.8394846],"study_design_scores_gemma":[0.001843967,0.00009270997,0.004721283,0.000269929,0.00001031869,0.00002553078,0.0003155424,0.9921903,0.00004296378,0.0002082608,0.00006592706,0.000213264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5474578,0.00001131446,0.4508561,0.0009375238,0.00006745735,0.0003020333,0.000001507902,0.00006527007,0.0003010504],"genre_scores_gemma":[0.9220263,0.00006894262,0.0750375,0.002567645,0.0001044121,0.0001116159,0.0000517077,0.00001224723,0.00001965163],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.991926,"threshold_uncertainty_score":0.6222379,"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."}}