{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07591517,0.003587698,0.01203873,0.01652945,0.001665541,0.01007598,0.009900671,0.009216417,0.06642471],"category_scores_gemma":[0.2589191,0.003751182,0.02244023,0.01391376,0.003225635,0.00464035,0.009488222,0.007741209,0.02987792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00410743,"about_ca_system_score_gemma":0.02087152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007045381,"about_ca_topic_score_gemma":0.01241236,"domain_scores_codex":[0.8814008,0.03953864,0.06083868,0.003681775,0.01302193,0.001518109],"domain_scores_gemma":[0.7569028,0.1603542,0.04213464,0.01162715,0.02724065,0.001740511],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001066052,0.00007219733,0.001105604,0.3189657,0.005727774,0.0003035265,0.0004529131,0.0005747081,0.0008846938,0.006044053,0.5012883,0.1635145],"study_design_scores_gemma":[0.002520348,0.0002377287,0.003987281,0.2967823,0.01062974,0.0009172818,0.0002782151,0.0006821824,0.001276816,0.01438137,0.6680536,0.0002531734],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.001234764,0.4386249,0.0937264,0.04820969,0.01582226,0.04635892,0.3175069,0.006374727,0.03214142],"genre_scores_gemma":[0.01116633,0.2477619,0.2715589,0.07481051,0.00625191,0.1873706,0.1662543,0.004082279,0.03074332],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9240848,"threshold_uncertainty_score":0.4014826,"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."}}