{"id":"W2894992918","doi":"10.5041/rmmj.10351","title":"Detection and Diagnostic Overall Accuracy Measures of Medical Tests","year":2018,"lang":"en","type":"article","venue":"Rambam Maimonides Medical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medical diagnosis; Diagnostic accuracy; Bayes' theorem; Population; Medicine; Test (biology); Accuracy and precision; Statistics; Contrast (vision); Diagnostic test; Sensitivity (control systems); Computer science; Machine learning; Artificial intelligence; Bayesian probability; Pathology; Pediatrics; Mathematics; Radiology; Environmental health","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":[0.01380728,0.000255144,0.0008474745,0.0001362116,0.0002056832,0.00009166194,0.0006430718,0.0006215332,0.003674387],"category_scores_gemma":[0.7756471,0.0001848472,0.000181955,0.0002094654,0.001352122,0.0001352833,0.0002706668,0.001368221,0.00003068846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006216358,"about_ca_system_score_gemma":0.0004075223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002506051,"about_ca_topic_score_gemma":0.00006517678,"domain_scores_codex":[0.9922522,0.001413847,0.001736216,0.0003382174,0.003758786,0.0005007752],"domain_scores_gemma":[0.8116107,0.1843949,0.0009299102,0.0004845421,0.0006202396,0.001959706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003069829,0.0005334633,0.005422232,0.0002121167,0.0002678787,0.0004542161,0.0002271032,1.826489e-7,0.0007667238,0.02158731,0.006779047,0.9634427],"study_design_scores_gemma":[0.001964109,0.000892281,0.02907258,0.001288376,0.0002033895,0.001481254,0.00006728849,0.0010176,0.002459709,0.9594238,0.001844794,0.000284775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.534174,0.0005188892,0.4552625,0.005060764,0.00317953,0.0004448293,0.0000143585,0.000121922,0.001223211],"genre_scores_gemma":[0.8807547,0.001155952,0.1144075,0.0006799749,0.002925249,0.0000104846,2.097979e-7,0.00004128041,0.00002464274],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.963158,"threshold_uncertainty_score":0.9972364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3770743818396729,"score_gpt":0.5377760369627361,"score_spread":0.1607016551230632,"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."}}