{"id":"W3183900947","doi":"10.3399/bjgpo.2021.0058","title":"Clinical judgment of GPs for the diagnosis of dementia: a diagnostic test accuracy study","year":2021,"lang":"en","type":"article","venue":"BJGP Open","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Population and Public Health","funders":"National Institute for Health and Care Research; Wellcome Trust","keywords":"Dementia; Medicine; Interquartile range; Confidence interval; Likelihood ratios in diagnostic testing; Test (biology); Clinical judgment; Diagnostic accuracy; Internal medicine; Pediatrics; Physical therapy; Disease","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00153293,0.0001066515,0.000420246,0.00003611392,0.00008238397,0.00004241075,0.0003803624,0.00003669249,0.001171039],"category_scores_gemma":[0.01889596,0.00006985856,0.0001740344,0.0002299469,0.00009900787,0.00008029784,0.000664126,0.0001255616,0.00001682624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001566845,"about_ca_system_score_gemma":0.0003165506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001328763,"about_ca_topic_score_gemma":0.0001020008,"domain_scores_codex":[0.9982709,0.0001634506,0.0006209713,0.0002858803,0.0004333977,0.0002254341],"domain_scores_gemma":[0.9813599,0.01736051,0.0001751663,0.0004742072,0.0005317864,0.00009844163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001723738,0.007147226,0.9349118,0.0001050039,0.0007831222,0.00004026345,0.0001543487,3.892125e-7,0.0001429899,0.00004725479,0.007857942,0.04863731],"study_design_scores_gemma":[0.005937985,0.003313764,0.9655592,0.0002035317,0.001176587,0.000004117775,0.002562709,0.00002685474,0.008912764,0.00007757497,0.01215098,0.00007394264],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862164,0.0011493,0.0002524062,0.003448094,0.0001417027,0.006307341,0.00006619236,0.000007201111,0.002411356],"genre_scores_gemma":[0.9957804,0.001026333,0.0003646089,0.0003941655,0.00007677211,0.001599909,0.00002476531,0.0000148042,0.0007182556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04856336,"threshold_uncertainty_score":0.999742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1271464472898594,"score_gpt":0.4702636970776792,"score_spread":0.3431172497878198,"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."}}