{"id":"W4407925758","doi":"10.1016/j.jclinepi.2025.111738","title":"Comparing Artificial Intelligence and manual methods in systematic review processes: protocol for a systematic review","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"College of Medicine, Nursing and Health Sciences, National University of Ireland, Galway; China Scholarship Council; University of Galway","keywords":"Systematic review; Protocol (science); Stage (stratigraphy); Medicine; Computer science; MEDLINE; Alternative medicine; Biology; 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":[0.1431003,0.006164024,0.01714885,0.01274362,0.004132661,0.007282666,0.005077409,0.008506878,0.09339406],"category_scores_gemma":[0.2422279,0.006760901,0.01955094,0.01427103,0.005641171,0.009272489,0.005503339,0.01094579,0.01473201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01545516,"about_ca_system_score_gemma":0.04961033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00383437,"about_ca_topic_score_gemma":0.008083622,"domain_scores_codex":[0.8762829,0.0694454,0.03465277,0.006104147,0.01036515,0.003149593],"domain_scores_gemma":[0.8265345,0.08675241,0.03139266,0.01736296,0.03408812,0.00386941],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.01072601,0.0005516942,0.0007415839,0.8645783,0.004343214,0.0005010162,0.002549159,0.001825733,0.001702868,0.007875227,0.05339647,0.0512087],"study_design_scores_gemma":[0.1067506,0.005291731,0.007366665,0.5569735,0.01168747,0.000872085,0.003020324,0.005290225,0.004878012,0.03144296,0.2651811,0.001245476],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"protocol","genre_gemma":"protocol","genre_scores_codex":[0.0001989861,0.0007607504,0.00200362,0.0002964675,0.0003468113,0.9941896,0.001824316,0.00009100592,0.0002884351],"genre_scores_gemma":[0.0001855142,0.0002611269,0.003545514,0.0001036755,0.00001893393,0.9956441,0.0001460847,0.000006529327,0.00008855465],"genre_candidate":"protocol","genre_consensus":"protocol","teacher_disagreement_score":0.8568997,"threshold_uncertainty_score":0.7567956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8548363439343531,"score_gpt":0.7538432043518545,"score_spread":0.1009931395824987,"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."}}