{"id":"W4386699918","doi":"10.1101/2023.09.12.23295381","title":"Randomized Controlled Trials Evaluating AI in Clinical Practice: A Scoping Evaluation","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Clinical trial; Randomized controlled trial; Medicine; Health care; Clinical Practice; Intervention (counseling); Systematic review; Alternative medicine; MEDLINE; Artificial intelligence; Medical physics; Family medicine; Nursing; Computer science; 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":[],"category_scores_codex":[0.1802356,0.00309485,0.01475101,0.009507031,0.00173489,0.006947519,0.004317932,0.007247429,0.01020343],"category_scores_gemma":[0.4667556,0.002085104,0.02263144,0.01090769,0.003880427,0.006799341,0.003106549,0.004016469,0.001380878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008135867,"about_ca_system_score_gemma":0.01592289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003475214,"about_ca_topic_score_gemma":0.006175924,"domain_scores_codex":[0.7436512,0.1459657,0.08312704,0.008057927,0.01729862,0.001899488],"domain_scores_gemma":[0.4474524,0.4562917,0.05554293,0.01280014,0.02615032,0.001762494],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.007528752,0.0002136828,0.00270102,0.846669,0.08263209,0.0001387789,0.0003367186,0.0008362198,0.0002131568,0.00181299,0.002255961,0.05466164],"study_design_scores_gemma":[0.01470547,0.003078444,0.003731831,0.7687979,0.1874018,0.0002432614,0.000405775,0.001069343,0.0005750031,0.004073848,0.01580955,0.0001077915],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01109612,0.9178167,0.01454067,0.004364435,0.001998948,0.04318866,0.003212644,0.0002632398,0.003518533],"genre_scores_gemma":[0.2808421,0.5103064,0.05358124,0.01167824,0.001631175,0.1371872,0.003535567,0.0002164094,0.001021696],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8197644,"threshold_uncertainty_score":0.9531885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6999636305230319,"score_gpt":0.6744827929932773,"score_spread":0.02548083752975461,"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."}}