{"id":"W3033545112","doi":"10.1038/s41591-020-0941-1","title":"Developing specific reporting guidelines for diagnostic accuracy studies assessing AI interventions: The STARD-AI Steering Group","year":2020,"lang":"en","type":"letter","venue":"Nature Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":258,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"NIHR Imperial Biomedical Research Centre; Singapore Eye Research Institute; National Institute for Health and Care Research; Imperial College London; DeepMind; University Hospitals Birmingham NHS Foundation Trust; Alan Turing Institute; Ottawa Hospital Research Institute; University of Ottawa","keywords":"Steering committee; Diagnostic accuracy; Psychological intervention; Medicine; Medical physics; Psychology; Psychiatry; Internal medicine; Engineering; Engineering management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5634648,0.003124339,0.009577018,0.01244165,0.006123103,0.01679768,0.0178256,0.05933649,0.006640607],"category_scores_gemma":[0.7099386,0.004507081,0.01377962,0.01082373,0.009548507,0.01020647,0.01368732,0.04887169,0.009722749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0120109,"about_ca_system_score_gemma":0.04983011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01089416,"about_ca_topic_score_gemma":0.009216843,"domain_scores_codex":[0.3965691,0.3395493,0.1928813,0.009239362,0.05357148,0.008189448],"domain_scores_gemma":[0.1177204,0.5547451,0.09341068,0.03085144,0.1889364,0.01433601],"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":[0.0006494218,0.0001192706,0.003263934,0.006046319,0.0006342927,0.0001943999,0.0008488227,0.0003840195,0.0006013988,0.01062698,0.9242712,0.05235999],"study_design_scores_gemma":[0.002773785,0.0003437572,0.007664443,0.05489454,0.001737837,0.0005564049,0.001326638,0.003108343,0.003037603,0.03106403,0.8930405,0.0004520405],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.0008979065,0.009419492,0.02243551,0.908173,0.03429951,0.007576159,0.005352497,0.0005743757,0.01127166],"genre_scores_gemma":[0.00668251,0.006189669,0.1104691,0.8175142,0.02215835,0.02573064,0.004288168,0.0005614642,0.006406002],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4365352,"threshold_uncertainty_score":0.5383257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6504306146423643,"score_gpt":0.604292360396703,"score_spread":0.04613825424566131,"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."}}