RT Journal Article
T1 Functional covariate-adjusted partial area under the specificity-ROC curve with an application to metabolic syndrome diagnosis
A1 Carvalho, Vanda Inácio de
A1 Carvalho, Miguel de
A1 Alonzo, Todd A.
A1 González Manteiga, Wenceslao
K1 Arterial oxygen saturation
K1 Average specificity
K1 Biomarker
K1 Functional covariate-adjustment
K1 Gamma-glutamyl transferase
K1 Kernel regression
K1 Metabolic syndrome
K1 Partial area under the curve
K1 Sensitivity
K1 Specificity-receiver operating characteristic curve
AB Due to recent advances in technology, medical diagnosis data are becoming increasingly complex and, nowadays, applications where measurements are curves or images are ubiquitous. Motivated by the need of modeling a functional covariate on a metabolic syndrome case study, we developa nonparametric functional regression model for the area under the specificity receiver operating characteristic curve. This partial area is a meaningfulsummary measure of diagnostic accuracy for cases in which misdiagnosisof diseased subjects may lead to serious clinical consequences, and hence itis critical to maintain a high sensitivity. Its normalized value can be interpreted as the average specificity over the interval of sensitivities considered,thus summarizing the trade-off between sensitivity and specificity. Our methods are motivated by, and applied to, a metabolic syndrome study that investigates how restricting the sensitivity of the gamma-glutamyl-transferase,a metabolic syndrome marker, to certain clinical meaningful values, affectsits corresponding specificity and how it might change for different curvesof arterial oxygen saturation. Application of our methods suggests that oxygen saturation is key to gamma-glutamyl transferase’s performance and thatsome of the different intervals of sensitivities considered offer a good tradeoff between sensitivity and specificity. The simulation study shows that theestimator associated with our model is able to recover successfully the trueoverall shape of the functional covariate-adjusted partial area under the curvein different complex scenarios
PB The Institute of Mathematical Statistics
SN 1932-6157
YR 2016
FD 2016
LK http://hdl.handle.net/10347/18566
UL http://hdl.handle.net/10347/18566
LA eng
NO Inácio de Carvalho, Vanda; de Carvalho, Miguel; Alonzo, Todd A.; González-Manteiga, Wenceslao. Functional covariate-adjusted partial area under the specificity-ROC curve with an application to metabolic syndrome diagnosis. Ann. Appl. Stat. 10 (2016), no. 3, 1472-1495. doi:10.1214/16-AOAS943
NO Partially funded by Fondecyt Grants 11130541 (first author) and 11121186 (second author). Supported in part by the Spanish Ministry of Science and Innovation through project MTM2008-03010
DS Minerva
RD 24 abr 2026