{"id":"W4396803002","doi":"10.1186/s12874-024-02217-2","title":"An evaluation of computational methods for aggregate data meta-analyses of diagnostic test accuracy studies","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Laplace's method; Generalized linear mixed model; Confidence interval; Statistics; Sensitivity (control systems); Algorithm; Computer science; Context (archaeology); Mathematics; Mean squared error; Bayesian probability","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","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9047644,0.0002831303,0.006772812,0.001408132,0.0001425268,0.0002101824,0.005192714,0.0002098868,0.01297965],"category_scores_gemma":[0.9947643,0.0001252191,0.001892509,0.003162774,0.001123175,0.0004022864,0.0009458951,0.0004306459,0.0001272872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004619322,"about_ca_system_score_gemma":0.002833514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007241531,"about_ca_topic_score_gemma":0.0001753917,"domain_scores_codex":[0.2334693,0.7073126,0.01926971,0.0033284,0.03576808,0.0008519165],"domain_scores_gemma":[0.00411485,0.9734258,0.002653365,0.005088094,0.01433134,0.0003865417],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000376657,0.0002362828,0.0003162769,0.001293426,0.01146913,0.000005560262,0.0007385001,0.002881097,0.001232998,0.008660562,0.0295978,0.9435307],"study_design_scores_gemma":[0.0002453442,0.0002429744,0.0003603321,0.0001114971,0.01043385,0.00001252087,0.001204467,0.6903214,0.0008817626,0.2862822,0.009802739,0.0001009689],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003442338,0.0878211,0.9050691,0.001590501,0.000327938,0.001428538,0.000183505,0.000006324837,0.0001306099],"genre_scores_gemma":[0.06673297,0.0009122665,0.9312292,0.00006845039,0.00017895,0.000434487,0.0001265156,0.00001878161,0.0002983774],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9434297,"threshold_uncertainty_score":0.9879226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9966886755845052,"score_gpt":0.8547950724739578,"score_spread":0.1418936031105474,"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."}}