{"id":"W3205551384","doi":"10.1038/s41591-021-01517-0","title":"A quality assessment tool for artificial intelligence-centered diagnostic test accuracy studies: QUADAS-AI","year":2021,"lang":"en","type":"letter","venue":"Nature Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":242,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ottawa Hospital; Hospital for Sick Children; University of Ottawa","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; NIHR Oxford Biomedical Research Centre; NIHR Imperial Biomedical Research Centre; Massachusetts General Hospital; UK Research and Innovation; Assistance publique-Hôpitaux de Paris; Institut National de la Santé et de la Recherche Médicale; Singapore Eye Research Institute; University of Ottawa; Imperial College London; Linköpings Universitet; Wellcome Trust; University College London; Cancer Research UK; Oxford University Hospitals NHS Foundation Trust; Amsterdam University Medical Centers; National Institutes of Health; University Hospitals Birmingham NHS Foundation Trust; Nuclear Power Institute of China; Universiteit van Amsterdam; Université de Paris; Ottawa Hospital Research Institute; University of Oxford; University of Leeds; National Institute for Health and Care Excellence; Massachusetts Institute of Technology; University of Pennsylvania; National Institute for Health and Care Research","keywords":"Test (biology); Diagnostic accuracy; Diagnostic test; Artificial intelligence; Computer science; Quality (philosophy); Quality assessment; Medical physics; Machine learning; External quality assessment; Medicine; Pathology; Biology; Internal medicine; Pediatrics","routes":{"ca_aff":true,"ca_fund":true,"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":["research_integrity"],"category_scores_codex":[0.002042185,0.0007939929,0.002083519,0.0004160975,0.0003482129,0.00006493617,0.0003961643,0.002630339,0.0007534189],"category_scores_gemma":[0.1300956,0.0006169447,0.0004400982,0.000760111,0.0004473013,0.0001358452,0.0001008875,0.00728417,0.0000546357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0011791,"about_ca_system_score_gemma":0.002043812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003348586,"about_ca_topic_score_gemma":0.0002343252,"domain_scores_codex":[0.9933081,0.0003387561,0.002522966,0.001320327,0.001521813,0.0009880145],"domain_scores_gemma":[0.9475916,0.04608738,0.0009628903,0.00142347,0.003649088,0.0002855616],"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":[0.000123197,0.0004014702,0.001153429,0.003871277,0.0003709783,0.0003740092,0.001555084,0.000001105992,0.0001725122,0.0004557577,0.8907975,0.1007237],"study_design_scores_gemma":[0.000222543,0.001964155,0.0005723989,0.006603742,0.001072965,0.0001230221,0.007313808,0.0001624729,0.002379854,0.01222737,0.966547,0.000810695],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.002526829,0.01317868,0.004713428,0.9641833,0.01105251,0.003742036,0.0001815215,0.0001547217,0.0002669793],"genre_scores_gemma":[0.07719712,0.003955501,0.001655481,0.8579056,0.05136105,0.00117469,0.004852813,0.0001473187,0.001750443],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.1280534,"threshold_uncertainty_score":0.9996282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3335800058022347,"score_gpt":0.5481464259654348,"score_spread":0.2145664201632001,"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."}}