{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.01285063,0.0005020809,0.002432931,0.0003578205,0.0009843375,0.0003051338,0.0005100012,0.000411361,0.0002112192],"category_scores_gemma":[0.09971938,0.000299938,0.000841679,0.0008457532,0.003792622,0.0003561387,0.0001421912,0.001209035,0.00003021539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001418503,"about_ca_system_score_gemma":0.002295358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001311407,"about_ca_topic_score_gemma":0.0002306299,"domain_scores_codex":[0.9882708,0.003207907,0.006537294,0.0005760088,0.0006887525,0.0007193038],"domain_scores_gemma":[0.9677248,0.02211252,0.003076248,0.0006331159,0.005954657,0.0004986653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01551698,0.0004083174,0.0001760867,0.0003930411,0.0009761487,0.0002622165,0.0196918,0.0010167,0.02484022,0.4700654,0.003686558,0.4629666],"study_design_scores_gemma":[0.000205342,0.0001798772,0.0000108938,0.0003245375,0.0005154223,0.001575538,0.02349684,0.009622499,0.4495582,0.5134379,0.0008668341,0.0002061096],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2750357,0.01185836,0.3545442,0.3517055,0.003847698,0.002855454,0.00002435662,0.0000474924,0.00008128323],"genre_scores_gemma":[0.9721737,0.002300252,0.01481077,0.00765822,0.00279693,0.0001528103,0.00002113682,0.00005568249,0.00003050758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.697138,"threshold_uncertainty_score":0.9999453,"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."}}