{"id":"W4414283105","doi":"10.1002/sim.70248","title":"The Estimand Framework in Diagnostic Accuracy Studies","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Diagnostic accuracy; Test (biology); Diagnostic test; Bridge (graph theory); Interpretation (philosophy)","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":["metaresearch"],"category_scores_codex":[0.2774242,0.005078632,0.008925077,0.01045436,0.001485923,0.007999614,0.007074516,0.008290183,0.006447696],"category_scores_gemma":[0.4363665,0.002796567,0.00804563,0.009412363,0.00964957,0.009861521,0.006450403,0.009957385,0.001378151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005982104,"about_ca_system_score_gemma":0.007799469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006735598,"about_ca_topic_score_gemma":0.002789548,"domain_scores_codex":[0.580865,0.3886494,0.00850451,0.01005258,0.01043757,0.001490785],"domain_scores_gemma":[0.3298799,0.6405106,0.0105384,0.01361594,0.004757913,0.0006972848],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004263883,0.0000969188,0.004088061,0.003832554,0.003285457,0.000575925,0.0007133166,0.03195218,0.0001880805,0.8881668,0.003250926,0.06342348],"study_design_scores_gemma":[0.0003135678,0.0002637443,0.0006766337,0.001159847,0.001047648,0.0002146863,0.0001170834,0.05403851,0.0003441201,0.9311106,0.01062619,0.00008736526],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001630997,0.01394566,0.9742231,0.004858778,0.0003790328,0.0006117469,0.0006099332,0.0002555498,0.003485212],"genre_scores_gemma":[0.137699,0.01382248,0.8306328,0.003949028,0.001743204,0.008505345,0.001024631,0.0002819849,0.002341561],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7225758,"threshold_uncertainty_score":0.8910646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6242570362789946,"score_gpt":0.6233312332906149,"score_spread":0.0009258029883797425,"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."}}