{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001112888,0.0001377351,0.0001722967,0.0001100494,0.00009120935,0.0002630064,0.0002546785,0.0001264597,0.00004701785],"category_scores_gemma":[0.0001537364,0.00009953589,0.00003053126,0.0002668655,0.00005067344,0.001125469,0.0001653171,0.0002510297,0.0000718825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005697272,"about_ca_system_score_gemma":0.0002370055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004313388,"about_ca_topic_score_gemma":0.000005104392,"domain_scores_codex":[0.998071,0.00006429556,0.0006760809,0.0001932699,0.0008121775,0.000183145],"domain_scores_gemma":[0.9991386,0.0002738189,0.0001143478,0.0001930848,0.00007856516,0.000201616],"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":[0.000002745755,0.00003731804,0.0001464926,0.0001834145,0.00002895621,0.00001798261,0.003603606,0.000002394838,0.000005185192,0.001141625,0.00007713799,0.9947531],"study_design_scores_gemma":[0.000277482,0.00005685951,0.0001980799,0.0004945087,0.00001667954,0.0001128205,0.0005682234,0.9947459,0.001260085,0.001385615,0.0006729424,0.0002107673],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2337296,0.00001680098,0.7650423,0.000344329,0.0003117032,0.0002139061,0.000002127809,0.0001818429,0.0001574032],"genre_scores_gemma":[0.2058402,0.00008249284,0.7933546,0.0004166565,0.0001105556,0.000127308,0.00002906016,0.000008888252,0.00003023101],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9947435,"threshold_uncertainty_score":0.4058956,"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."}}