{"id":"W4406152263","doi":"10.1038/s41591-024-03425-5","title":"The TRIPOD-LLM reporting guideline for studies using large language models","year":2025,"lang":"en","type":"review","venue":"Nature Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":355,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Alberta","funders":"National Institute on Minority Health and Health Disparities; National Center for Advancing Translational Sciences; U.S. National Library of Medicine; Department of Health and Social Care; National Cancer Institute; National Institutes of Health; National Science Foundation; Cancer Research UK; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Radiological Society of North America; Fogarty International Center; National Heart, Lung, and Blood Institute; National Institute of Biomedical Imaging and Bioengineering; Gordon and Betty Moore Foundation","keywords":"Tripod (photography); Checklist; Guideline; Standardization; Computer science; Health care; Comparability; Delphi; Medicine; Psychology; Engineering; Political science","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":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008336406,0.0006543772,0.003988189,0.0003921105,0.0005325318,0.00002781365,0.000406938,0.0007811625,0.00001627095],"category_scores_gemma":[0.05526782,0.0003223278,0.0007765262,0.0007248374,0.0002600291,0.0000484524,0.0002006067,0.003430161,0.000001243421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003138226,"about_ca_system_score_gemma":0.0008175445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002199308,"about_ca_topic_score_gemma":0.000006573379,"domain_scores_codex":[0.9938525,0.0001822247,0.003761016,0.0007336306,0.0007536492,0.0007169875],"domain_scores_gemma":[0.9926697,0.002575503,0.002970837,0.0009301843,0.0006443617,0.0002094091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003191302,0.00004267563,0.000001429672,0.02819377,0.0009585471,0.0002135133,0.0002806968,0.000008094994,0.000004304574,0.00111989,0.08593412,0.883211],"study_design_scores_gemma":[0.001364914,0.0001152713,1.421015e-7,0.05952769,0.004856208,0.0003680569,0.0005592989,0.008272637,0.000001103647,0.0004460262,0.9242456,0.0002430421],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003773108,0.9779376,0.009191836,0.006553353,0.002724319,0.002066682,0.00002986816,0.0001331327,0.001359412],"genre_scores_gemma":[0.00001014823,0.9781941,0.007612108,0.003651921,0.004384447,0.0001234748,0.0004588628,0.0001071825,0.005457785],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.882968,"threshold_uncertainty_score":0.9999229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07907597815907866,"score_gpt":0.5092562311739407,"score_spread":0.4301802530148621,"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."}}