{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08024682,0.002773568,0.005926598,0.009348676,0.00188862,0.00995888,0.004947692,0.0128089,0.003414056],"category_scores_gemma":[0.3890695,0.00181909,0.002086416,0.003497421,0.004467012,0.00417147,0.001301546,0.01345028,0.002107963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00324551,"about_ca_system_score_gemma":0.00443567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001851321,"about_ca_topic_score_gemma":0.004036116,"domain_scores_codex":[0.9514142,0.01763093,0.008425372,0.002654074,0.0193461,0.0005295055],"domain_scores_gemma":[0.4328516,0.4458162,0.009978031,0.005364418,0.1024545,0.003535231],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002592253,0.00005536996,0.001006352,0.002228581,0.0006539724,0.0002233832,0.00009688296,0.0001536218,0.0001692165,0.001484278,0.9323429,0.06132619],"study_design_scores_gemma":[0.001301299,0.0006262048,0.01616712,0.009242566,0.004066041,0.00168286,0.0005245077,0.009792511,0.001881029,0.01941852,0.9348271,0.0004701648],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0004112877,0.02479218,0.001872567,0.05585437,0.915365,0.00009908125,0.0001502647,0.0001155819,0.001339668],"genre_scores_gemma":[0.004764235,0.01044521,0.002525446,0.02003334,0.9599143,0.0001381683,0.00008320827,0.00008581062,0.002010159],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.9197532,"threshold_uncertainty_score":0.4243909,"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."}}