{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08704706,0.001766844,0.002810809,0.002991116,0.0008393388,0.002168776,0.003448882,0.001915865,0.003480095],"category_scores_gemma":[0.277885,0.001069126,0.004602006,0.003323358,0.001036557,0.002164585,0.002548413,0.002617545,0.0003654346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002368168,"about_ca_system_score_gemma":0.005966612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008651863,"about_ca_topic_score_gemma":0.01030241,"domain_scores_codex":[0.9484687,0.0465441,0.001502352,0.001103022,0.002174571,0.0002072468],"domain_scores_gemma":[0.5765346,0.397782,0.007547763,0.009422135,0.008000313,0.0007133015],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001153189,0.0001483429,0.008001778,0.003843666,0.005422518,0.0003007482,0.0004406935,0.7911577,0.0005687904,0.0452433,0.004608285,0.1391111],"study_design_scores_gemma":[0.000606044,0.0002221675,0.001192357,0.0007051983,0.001236485,0.0001614738,0.0000903273,0.9577057,0.0004159913,0.03386573,0.003742421,0.000056012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02062627,0.007364871,0.9649078,0.002371109,0.0002796569,0.0008604123,0.0008006986,0.000708573,0.002080647],"genre_scores_gemma":[0.1699072,0.002989044,0.8214642,0.0009354687,0.0001713653,0.003169105,0.0006144451,0.0002528078,0.0004963878],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.912953,"threshold_uncertainty_score":0.4603543,"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."}}