{"id":"W2157472158","doi":"10.1136/bmj.d4770","title":"Verification problems in diagnostic accuracy studies: consequences and solutions","year":2011,"lang":"en","type":"article","venue":"BMJ","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Victoria Hospital","funders":"","keywords":"Receiver operating characteristic; Diagnostic accuracy; Diagnostic odds ratio; Gold standard (test); Statistics; Test (biology); Outcome (game theory); Diagnostic test; Sensitivity (control systems); Nominal level; Computer science; Medicine; Mathematics; Confidence interval; Radiology; Pediatrics","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":["metaresearch","insufficient_payload"],"category_scores_codex":[0.05342846,0.0001076563,0.0009912517,0.0001737506,0.00009514456,0.0001461275,0.0004515723,0.00003274066,0.001149478],"category_scores_gemma":[0.2059477,0.00005246207,0.0001753671,0.0006393546,0.0002012875,0.0002238065,0.00006970592,0.00005486783,0.001094583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001536028,"about_ca_system_score_gemma":0.00004350357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000574916,"about_ca_topic_score_gemma":0.0002302091,"domain_scores_codex":[0.9915858,0.002738459,0.004051741,0.0004485355,0.001030849,0.000144601],"domain_scores_gemma":[0.9849422,0.01098648,0.002108895,0.001406495,0.0004893052,0.00006662624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007977275,0.0002852075,0.5247063,0.0002601278,0.0004956009,0.00003059826,0.03712191,0.0001449923,0.0004246728,0.06437641,0.3002782,0.07186796],"study_design_scores_gemma":[0.000448821,0.0001130138,0.6065461,0.0003571887,0.0002999943,0.00005631621,0.0177825,0.002865754,0.00007180479,0.2643844,0.106583,0.0004911765],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8586237,0.04491381,0.01650018,0.0175472,0.001215854,0.007573214,0.00003192783,0.00003215467,0.05356194],"genre_scores_gemma":[0.9958986,0.0004708631,0.002383445,0.0001085486,0.00002422632,0.000215839,9.905317e-7,0.00000265295,0.000894845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.200008,"threshold_uncertainty_score":0.9997636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9023707166369184,"score_gpt":0.5668338398689057,"score_spread":0.3355368767680127,"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."}}