{"id":"W4361994586","doi":"10.2196/44597","title":"Chinese Clinical Named Entity Recognition From Electronic Medical Records Based on Multisemantic Features by Using Robustly Optimized Bidirectional Encoder Representation From Transformers Pretraining Approach Whole Word Masking and Convolutional Neural Networks: Model Development and Validation","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Convolutional neural network; Natural language processing; Artificial intelligence; Medical diagnosis; Encoder; 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":[0.001961476,0.0002676334,0.0003958543,0.0002141232,0.000355152,0.0001813623,0.0003105509,0.0004657372,0.00004018191],"category_scores_gemma":[0.0009498129,0.0002410994,0.00007772585,0.0005362586,0.0001567975,0.0007175613,0.0001350051,0.001268966,0.000003235062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000140877,"about_ca_system_score_gemma":0.0005507144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001590563,"about_ca_topic_score_gemma":0.00003714506,"domain_scores_codex":[0.9959467,0.0004201535,0.001104555,0.0004512194,0.001604479,0.0004728749],"domain_scores_gemma":[0.9976481,0.001290648,0.0003351814,0.0001984879,0.000104062,0.0004234995],"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":[0.0002946374,0.0002209799,0.02249046,0.0001862299,0.0001362915,0.000009558204,0.00853395,0.4352426,0.000007177211,0.00003602735,0.0007912045,0.5320508],"study_design_scores_gemma":[0.001955337,0.00005090724,0.009667301,0.0002159323,0.00001719698,0.00001202561,0.0002143848,0.9873564,0.000005914062,0.0002275685,0.00002737264,0.0002496732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4513492,0.00003956598,0.5473912,0.0004825953,0.0002313305,0.0002951772,0.00001506157,0.0001708799,0.00002505707],"genre_scores_gemma":[0.8092697,0.0001019308,0.1874531,0.0007894873,0.0002054176,0.00009690481,0.002049872,0.00002194093,0.00001160781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5521138,"threshold_uncertainty_score":0.983175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04777504155592551,"score_gpt":0.3528988721904299,"score_spread":0.3051238306345044,"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."}}