{"id":"W4404917089","doi":"10.2196/60334","title":"Chinese Clinical Named Entity Recognition With Segmentation Synonym Sentence Synthesis Mechanism: Algorithm Development and Validation","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Conditional random field; Natural language processing; Named-entity recognition; Sentence; Vocabulary; Segmentation; Synonym (taxonomy); Machine learning; 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":[0.004101771,0.001294812,0.001138065,0.00149531,0.0007626925,0.001002864,0.002581604,0.001508713,0.004684125],"category_scores_gemma":[0.007626805,0.000407476,0.000972254,0.001248234,0.0005212735,0.001991199,0.001369054,0.001614379,0.00227706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001348801,"about_ca_system_score_gemma":0.003400555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01679235,"about_ca_topic_score_gemma":0.01275213,"domain_scores_codex":[0.9984133,0.0004011846,0.0001975043,0.0006068976,0.0002719653,0.0001092115],"domain_scores_gemma":[0.9968565,0.001453812,0.0001688557,0.0004741845,0.0009390565,0.0001075877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008692971,0.0006150153,0.008509499,0.0005965041,0.0003260368,0.0003770989,0.0002373683,0.1345604,0.01245249,0.002874312,0.02255265,0.8160294],"study_design_scores_gemma":[0.0001413231,0.0001804892,0.001757571,0.00002687,0.00005915724,0.0001532647,0.0001023026,0.9806994,0.01236507,0.001318702,0.003168123,0.00002768826],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2557971,0.002625754,0.691347,0.001175016,0.0004899476,0.002184176,0.005282599,0.03628878,0.004809613],"genre_scores_gemma":[0.3737771,0.0007193311,0.6011358,0.0004112048,0.00009285602,0.00171562,0.01807719,0.0004435463,0.003627308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01679235,"threshold_uncertainty_score":0.03338921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03013081880966618,"score_gpt":0.3196210585014545,"score_spread":0.2894902396917883,"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."}}