Robust and flexible inference for the covariate‐specific receiver operating characteristic curve

Inácio, Vanda; Lourenço, Vanda; Carvalho, Miguel de; Parker, Richard; Gnanapragasam, Vincent

doi:10.1002/sim.9153

Cited by 4 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous research has focused on extending statistical methodology for ROC curve estimation to address issues such as adjustment for covariates, 3 , 4 incorporating censoring due to instrument detection limits 5 , 6 and robustness to model misspecification. 7 In addition, a wide variety of parametric and nonparametric methods have been proposed within frequentist and Bayesian paradigms (see Inácio et al 8 for a recent review). However, there is no consensus on an analytic approach that can handle all these issues simultaneously.…”

Section: Introductionmentioning

confidence: 99%

Estimating transformations for evaluating diagnostic tests with covariate adjustment

Sewak

Hothorn

2023

Stat Methods Med Res

View full text Add to dashboard Cite

Receiver operating characteristic analysis is one of the most popular approaches for evaluating and comparing the accuracy of medical diagnostic tests. Although various methodologies have been developed for estimating receiver operating characteristic curves and their associated summary indices, there is no consensus on a single framework that can provide consistent statistical inference while handling the complexities associated with medical data. Such complexities might include non-normal data, covariates that influence the diagnostic potential of a test, ordinal biomarkers or censored data due to instrument detection limits. We propose a regression model for the transformed test results which exploits the invariance of receiver operating characteristic curves to monotonic transformations and accommodates these features. Simulation studies show that the estimates based on transformation models are unbiased and yield coverage at nominal levels. The methodology is applied to a cross-sectional study of metabolic syndrome where we investigate the covariate-specific performance of weight-to-height ratio as a non-invasive diagnostic test. Software implementations for all the methods described in the article are provided in the tram add-on package to the R system for statistical computing and graphics.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimating transformations for evaluating diagnostic tests with covariate adjustment

Sewak

Hothorn

2023

Stat Methods Med Res

View full text Add to dashboard Cite

show abstract

“…Previous research has focused on extending statistical methodology for ROC curve estimation to address issues such as adjustment for covariates (Pepe 1997(Pepe , 1998(Pepe , 2000Faraggi 2003), incorporating censoring due to instrument detection limits (Perkins et al 2007;Ruopp et al 2008;Bantis et al 2017), comparing correlated diagnostic tests (Hanley and McNeil 1983;DeLong et al 1988;Zou and Hall 2002;Molodianovitch et al 2006;Bantis and Feng 2016) and robustness to model misspecification (Bianco et al 2020;Inácio et al 2021a). In addition, a wide variety of parametric and nonparametric methods have been proposed within frequentist and Bayesian paradigms (Hsieh and Turnbull 1996;Alonzo and Pepe 2002;Erkanli et al 2006;Branscum et al 2008;Yao et al 2010;González-Manteiga et al 2011;Rodríguez-Álvarez et al 2011;Cai and Pepe 2002;Cai and Moskowitz 2004;Inácio et al 2013;Ghosal et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Transformation models for ROC analysis

Sewak¹,

Hothorn²

2022

Preprint

View full text Add to dashboard Cite

Receiver operating characteristic (ROC) analysis is one of the most popular approaches for evaluating and comparing the accuracy of medical diagnostic tests. Although various methodologies have been developed for estimating ROC curves and its associated summary indices, there is no consensus on a single framework that can provide consistent statistical inference whilst handling the complexities associated with medical data. Such complexities might include covariates that influence the diagnostic potential of a test, ordinal test data, censored data due to instrument detection limits or correlated biomarkers. We propose a regression model for the transformed test results which exploits the invariance of ROC curves to monotonic transformations and naturally accommodates these features. Our use of maximum likelihood inference guarantees asymptotic efficiency of the resulting estimators and associated confidence intervals. Simulation studies show that the estimates based on transformation models are unbiased and yield coverage at nominal levels. The methodology is applied to a cross-sectional study of metabolic syndrome where we investigate the covariate-specific performance of weight-to-height ratio as a noninvasive diagnostic test. Software implementations for all the methods described in the article are provided in the tram R package.

show abstract

Ultrasonic renal length as an indicator of renal fibrosis severity in non-diabetic patients with chronic kidney disease

Chen,

Jiang,

Gunda

et al. 2024

Clin Exp Nephrol

View full text Add to dashboard Cite

Background Debate continues regarding the potential of the ultrasonic renal length to serve as an indicator for evaluating the advancement of renal fibrosis in chronic kidney disease (CKD). This study investigates the independent association between renal length and renal fibrosis in non-diabetic CKD patients and assesses its diagnostic performance. Methods From April 2019 to December 2021, 144 non-diabetic patients diagnosed with CKD who underwent a renal ultrasound examination and kidney biopsy were prospectively enrolled. Patients were categorized into the mild fibrosis group (n = 70) and the moderate-severe group (n = 74) based on the extent of fibrotic involvement. Ultrasonic renal length was measured from pole-to-pole in the coronal plane. A receiver operating characteristic (ROC) curve, multivariable logistic regression analysis, and a generalized additive model were performed. Results A negative linear correlation was found between renal length and moderate-severe renal fibrosis risk. Each centimeter increase in renal length decreased the odds of moderate-severe fibrosis by 38% (OR: 0.62; 95% CI 0.41–0.93; P = 0.020). After adjusting for confounders, the relationship persisted (OR: 0.58; 95% CI 0.33–1.00; P = 0.048). However, renal length presented limited discrimination ability in distinguishing degrees of renal fibrosis while controlling the key confounding factors, yielding an area under the ROC curve of only 0.58 (95% CI 0.45–0.70). Conclusion While an inverse relationship exists between renal length and risk of having moderate-severe renal fibrosis in non-diabetic CKD patients, renal length alone is insufficient for diagnosing fibrosis severity, underscoring the need for additional diagnostic parameters in CKD assessment.

show abstract

Robust and flexible inference for the covariate‐specific receiver operating characteristic curve

Cited by 4 publications

References 29 publications

Estimating transformations for evaluating diagnostic tests with covariate adjustment

Estimating transformations for evaluating diagnostic tests with covariate adjustment

Transformation models for ROC analysis

Ultrasonic renal length as an indicator of renal fibrosis severity in non-diabetic patients with chronic kidney disease

Contact Info

Product

Resources

About