{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002456511,0.0005390652,0.001362278,0.0003101976,0.0005926162,0.0001041803,0.0003368904,0.0008959913,0.00005960229],"category_scores_gemma":[0.157076,0.0003353196,0.0004185524,0.000622465,0.0002651975,0.0002322424,0.0001219587,0.005600388,0.00001315967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005943328,"about_ca_system_score_gemma":0.0005492792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001162908,"about_ca_topic_score_gemma":0.00005073451,"domain_scores_codex":[0.9936259,0.0001553204,0.003901405,0.000813176,0.0008883324,0.0006159071],"domain_scores_gemma":[0.9835266,0.008553872,0.002845035,0.0007533451,0.004181681,0.0001394056],"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":[0.00002619023,0.00001411629,0.0004950364,0.004927831,0.0002674345,0.0003372821,0.001387267,0.00000210088,0.00006460016,0.0001558528,0.922364,0.06995831],"study_design_scores_gemma":[0.0001482112,0.0002948174,0.0003740523,0.02517259,0.0006626665,0.0001816867,0.007128329,0.0000887806,0.00044508,0.004029731,0.9611284,0.0003457337],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.001196104,0.08278888,0.02425857,0.8808719,0.008759922,0.001918814,0.000009269458,0.0001606097,0.00003594379],"genre_scores_gemma":[0.0166007,0.005976983,0.0066175,0.9118862,0.05707549,0.0004410305,0.0009364447,0.0001267539,0.0003388983],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.1546195,"threshold_uncertainty_score":0.9999099,"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."}}