{"id":"W4414183234","doi":"10.1038/s41591-025-03953-8","title":"The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence","year":2025,"lang":"en","type":"review","venue":"Nature Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":132,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"National Institute for Health and Care Research; NIHR Imperial Biomedical Research Centre; Cancer Research UK","keywords":"Checklist; Generalizability theory; Diagnostic accuracy; Guideline; Test (biology); Delphi method; Delphi; Process (computing)","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":[0.06469003,0.002968556,0.01294541,0.01895701,0.001630096,0.008198003,0.01214522,0.008976732,0.01061164],"category_scores_gemma":[0.1911515,0.002513267,0.02226491,0.0121471,0.003298042,0.004020979,0.007157498,0.007606381,0.007340974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00751562,"about_ca_system_score_gemma":0.02689364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009032589,"about_ca_topic_score_gemma":0.01230222,"domain_scores_codex":[0.8764767,0.03188528,0.0660545,0.003575947,0.02036303,0.00164456],"domain_scores_gemma":[0.8050793,0.1067144,0.03873056,0.005072116,0.04275888,0.001644659],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000725865,0.00008906848,0.001992404,0.3690405,0.008129824,0.0002530172,0.0004636651,0.0007539068,0.00100478,0.01038585,0.2700071,0.3371539],"study_design_scores_gemma":[0.001238392,0.0002906,0.004298322,0.4636187,0.01739421,0.0009271059,0.0002558177,0.0008598841,0.0012942,0.01092445,0.498685,0.0002132503],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.0007173102,0.8907677,0.02183868,0.03133244,0.01090995,0.009169115,0.02284444,0.001047813,0.01137256],"genre_scores_gemma":[0.01057163,0.683032,0.1661654,0.05298198,0.005652794,0.02911215,0.04246609,0.0007691029,0.009248942],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9353099,"threshold_uncertainty_score":0.3421177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5482209524080598,"score_gpt":0.6473424222534527,"score_spread":0.09912146984539294,"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."}}