{"id":"W2898607795","doi":"10.2196/medinform.9965","title":"Clinical Named Entity Recognition From Chinese Electronic Health Records via Machine Learning Methods","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Conditional random field; Artificial intelligence; Natural language processing; F1 score; Machine learning; Named-entity recognition; Test set; Benchmark (surveying); Precision and recall; Health records; Deep learning; Information retrieval; Unstructured data; Task (project management); Data mining; Big data; Health care","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":[0.002478495,0.001306253,0.0008932409,0.005146448,0.0008324764,0.001327487,0.001807836,0.001270442,0.002101494],"category_scores_gemma":[0.009075345,0.0003231578,0.001484131,0.004643659,0.0005607238,0.002930562,0.001323697,0.001169658,0.001585332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001430319,"about_ca_system_score_gemma":0.002965925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01654226,"about_ca_topic_score_gemma":0.01288507,"domain_scores_codex":[0.9973739,0.0005485427,0.00042663,0.001139057,0.0003465846,0.0001652858],"domain_scores_gemma":[0.9954118,0.002327,0.0006195296,0.0007545461,0.0007970575,0.00009008124],"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":[0.0004030159,0.0002604105,0.01706992,0.0008703994,0.0002326463,0.001551642,0.0006136375,0.0484626,0.008216026,0.006262977,0.02652169,0.8895351],"study_design_scores_gemma":[0.00008243589,0.0001247474,0.01378458,0.0001738357,0.0002762973,0.0008878089,0.000418288,0.9296634,0.01715425,0.01353256,0.02377579,0.0001260267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1936822,0.006740324,0.7453144,0.002982043,0.0007690145,0.001370296,0.02747837,0.01432529,0.00733811],"genre_scores_gemma":[0.4850488,0.002086957,0.4526143,0.0006222734,0.0004083583,0.000778391,0.05387522,0.0001852472,0.00438039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01654226,"threshold_uncertainty_score":0.03289193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04074273956746675,"score_gpt":0.4129983582792558,"score_spread":0.372255618711789,"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."}}