{"id":"W4409572808","doi":"10.1007/s00464-025-11723-3","title":"Large language model-generated clinical practice guideline for appendicitis","year":2025,"lang":"en","type":"article","venue":"Surgical Endoscopy","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Guideline; Appendicitis; Clinical Practice; Medicine; Computer science; General surgery; Family medicine; Pathology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001447008,0.0001368865,0.0003633882,0.00009919856,0.0001429422,0.00002265342,0.00009068137,0.0002164384,0.0003096058],"category_scores_gemma":[0.002830732,0.0001175534,0.0001681925,0.0003000288,0.00005902476,0.00009232458,0.00003248997,0.0003026007,0.0000963581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007367,"about_ca_system_score_gemma":0.0005745667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001964553,"about_ca_topic_score_gemma":0.0000292762,"domain_scores_codex":[0.9979348,0.0001101205,0.001003333,0.0003655753,0.0001952973,0.0003908906],"domain_scores_gemma":[0.9978684,0.001005041,0.0001197127,0.0003186722,0.0004893552,0.0001988012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01211547,0.00403462,0.006932889,0.0005841816,0.0004748651,0.0004659653,0.002280294,0.000626143,0.001397854,0.09456008,0.6570777,0.2194499],"study_design_scores_gemma":[0.001736318,0.0003415003,0.00002258623,0.0001157999,0.0001695302,0.00003096801,0.001791447,0.07435384,0.01002799,0.001726381,0.9095356,0.0001480168],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5192229,0.005983279,0.2833622,0.09941349,0.005201154,0.00361155,0.0002140248,0.0005677234,0.08242362],"genre_scores_gemma":[0.9091784,0.0007209078,0.0553131,0.02467789,0.00168545,0.0001942836,0.000745729,0.00003892146,0.007445264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3899556,"threshold_uncertainty_score":0.4793689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1200831951731252,"score_gpt":0.5367283093942888,"score_spread":0.4166451142211637,"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."}}