{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005497708,0.0006086935,0.002829063,0.0003984557,0.0007828415,0.00004177964,0.0003659213,0.0009428441,0.00003477705],"category_scores_gemma":[0.3212413,0.0003339323,0.0005423084,0.001151296,0.0004115409,0.00007442132,0.0001114302,0.002296979,0.00001111342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006185594,"about_ca_system_score_gemma":0.002772699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001494989,"about_ca_topic_score_gemma":0.0001198271,"domain_scores_codex":[0.9911727,0.0001914742,0.00656227,0.0007725431,0.0006383494,0.0006626739],"domain_scores_gemma":[0.9557981,0.03378369,0.005123097,0.00134814,0.00366092,0.0002860423],"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":[0.00004188581,0.00003953431,0.000005042578,0.02087002,0.0002812855,0.00003334768,0.0002790962,0.000002439857,0.00000104477,0.002877597,0.01885868,0.95671],"study_design_scores_gemma":[0.00001983926,0.0002530755,3.98361e-7,0.06303502,0.003115321,0.0001165761,0.00222002,0.0001358806,0.00007739745,0.01150287,0.9192744,0.000249164],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000008696291,0.9606043,0.008149733,0.01898802,0.008136445,0.003912462,0.00001942958,0.00008441216,0.000096565],"genre_scores_gemma":[0.0001208735,0.9855834,0.001841294,0.002880001,0.008426712,0.0004224286,0.0003159435,0.00006430723,0.0003450961],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9564609,"threshold_uncertainty_score":0.9999112,"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."}}