{"id":"W4224306105","doi":"10.1016/j.ajodo.2021.12.007","title":"Assessing the performance of diagnostic test accuracy measures","year":2022,"lang":"en","type":"editorial","venue":"American Journal of Orthodontics and Dentofacial Orthopedics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"St. Michael's Hospital","funders":"","keywords":"Test (biology); Statistics; Computer science; Medicine; Mathematics; Geology","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02184888,0.0004110729,0.001396685,0.0003895632,0.0005760572,0.0007672479,0.001774434,0.000169399,0.0001354457],"category_scores_gemma":[0.212046,0.0002463105,0.0005297653,0.001106213,0.001027905,0.0006005505,0.0005312237,0.001762565,0.000003339313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000110127,"about_ca_system_score_gemma":0.001414537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007793329,"about_ca_topic_score_gemma":0.00003572183,"domain_scores_codex":[0.985832,0.001205574,0.002876634,0.0004676241,0.00920928,0.0004088617],"domain_scores_gemma":[0.9162812,0.0722749,0.007000273,0.0008452461,0.003313883,0.0002845103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009345772,0.0002479072,0.5051841,0.00005392401,0.0001627789,0.00004983518,0.000709268,0.0004998498,0.00002647256,0.00001305382,0.1934971,0.2994622],"study_design_scores_gemma":[0.0004310415,0.00185749,0.02282261,0.0002014809,0.0004067413,0.00003051205,0.002427095,0.0001159504,0.00001458637,0.00009555662,0.9712836,0.0003133305],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6207663,0.002362045,0.001672619,0.0006154376,0.373812,0.0003488511,0.0001392196,0.000009053649,0.0002745118],"genre_scores_gemma":[0.7091876,0.03126914,0.002007918,0.0002454175,0.2568267,0.00001630599,0.00001969503,0.00007836707,0.0003488339],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7777865,"threshold_uncertainty_score":0.9999989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06976136545771053,"score_gpt":0.3884011828602047,"score_spread":0.3186398174024941,"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."}}