{"id":"W3137957538","doi":"10.1016/j.jid.2021.02.744","title":"Raising the Bar for Randomized Trials Involving Artificial Intelligence: The SPIRIT-Artificial Intelligence and CONSORT-Artificial Intelligence Guidelines","year":2021,"lang":"en","type":"article","venue":"Journal of Investigative Dermatology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Women's College Hospital; University of Toronto","funders":"Alan Turing Institute","keywords":"Generalizability theory; Protocol (science); Randomized controlled trial; Psychological intervention; Consolidated Standards of Reporting Trials; Artificial intelligence; Clinical trial; Medicine; Gold standard (test); Computer science; Medical physics; Psychology; Alternative medicine; Nursing; Pathology","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":["metaresearch"],"category_scores_codex":[0.6504728,0.00434304,0.02362616,0.009515517,0.005768987,0.02215703,0.0133407,0.05593728,0.006238899],"category_scores_gemma":[0.7907294,0.005343796,0.02734545,0.01027393,0.01652948,0.01514292,0.007557943,0.07037636,0.005993159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009806117,"about_ca_system_score_gemma":0.02300372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00277464,"about_ca_topic_score_gemma":0.003560451,"domain_scores_codex":[0.187036,0.6678625,0.09830143,0.01165853,0.03248835,0.002653209],"domain_scores_gemma":[0.07604111,0.8471909,0.02431769,0.02503967,0.0226744,0.004736297],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01633946,0.0005360969,0.002788228,0.1276267,0.03331358,0.0007572912,0.005161141,0.003711128,0.001288171,0.1916437,0.3591044,0.2577302],"study_design_scores_gemma":[0.03889861,0.001554006,0.005154101,0.1975912,0.02146117,0.001175379,0.000896755,0.0242181,0.002095927,0.3879245,0.3179123,0.001118147],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.002510481,0.1244236,0.2619096,0.4370202,0.1199117,0.03198182,0.00407528,0.004731499,0.01343593],"genre_scores_gemma":[0.03547079,0.02372815,0.5173689,0.3000304,0.03363604,0.08129022,0.00232731,0.002087958,0.004060291],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3495272,"threshold_uncertainty_score":0.4310293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.55588047413655,"score_gpt":0.5015536799554129,"score_spread":0.05432679418113706,"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."}}