{"id":"W7117367844","doi":"10.1016/j.imed.2025.12.008","title":"The performance of Covidence: An artificial intelligence-based tool for title and abstract screening in a breast cancer evidence-based clinical practice guideline","year":2025,"lang":"en","type":"article","venue":"Intelligent Medicine","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Health Sciences; Population Health Research Institute; McMaster University; Impact","funders":"Hamilton Health Sciences Foundation","keywords":"Workload; Clinical Practice; Guideline; Clinical trial; Breast cancer; Stage (stratigraphy); Identification (biology)","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"],"consensus_categories":[],"category_scores_codex":[0.006054873,0.000140813,0.0003486572,0.0001509388,0.00007523613,0.00001748426,0.0001512207,0.0001011392,0.0003911078],"category_scores_gemma":[0.01609654,0.0000954639,0.0000703209,0.0003321035,0.0003098396,0.0001982745,0.00002805274,0.0003221004,0.000008270874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006395066,"about_ca_system_score_gemma":0.000683297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004666362,"about_ca_topic_score_gemma":0.0001077141,"domain_scores_codex":[0.9969501,0.0001200822,0.002041653,0.0003046082,0.0003801279,0.0002033699],"domain_scores_gemma":[0.9893829,0.008951554,0.0004380977,0.0003342401,0.0008059001,0.00008737372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004728872,0.0002651539,0.03017485,0.0002235192,0.00006214444,0.000006935985,0.00005311837,0.0006797067,0.000451085,0.0005774733,0.009380101,0.953397],"study_design_scores_gemma":[0.003752287,0.004182338,0.08483238,0.01173318,0.001582411,0.00004402829,0.003927205,0.6526166,0.01069856,0.001295691,0.2247519,0.0005833838],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3039172,0.006091665,0.3246824,0.3579584,0.002529341,0.003842949,0.00005800696,0.00009807799,0.0008219838],"genre_scores_gemma":[0.9699946,0.002830594,0.01396409,0.01230171,0.0006435313,0.00008485148,0.00003682847,0.0000196942,0.0001241171],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9528136,"threshold_uncertainty_score":0.9921913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.361299736082622,"score_gpt":0.5694698143195533,"score_spread":0.2081700782369313,"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."}}