Bayesian Nonparametric Approaches for ROC Curve Inference

Carvalho, Vanda Inacio de; Jara, Alejandro; Carvalho, Miguel de

doi:10.1007/978-3-319-19518-6_16

Cited by 10 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, when continuous covariates are involved, they used a semiparametric estimator to adjust for covariate effects over the entire biomarker distribution, not specifically targeting the sensitivity/specificity of interest. A few previous works have also adopted Bayesian modeling framework by incorporating the covariate effects in the parameters of the ROC curve associated data distributions (de Carvalho et al., 2013; de Carvalho and Rodriguez‐Alvarez, 2018).…”

Section: Introductionmentioning

confidence: 99%

Covariate adjustment in continuous biomarker assessment

Huang

Patil

et al. 2021

Biometrics

View full text Add to dashboard Cite

Continuous biomarkers are common for disease screening and diagnosis. To reach a dichotomous clinical decision, a threshold would be imposed to distinguish subjects with disease from nondiseased individuals. Among various performance metrics, specificity at a controlled sensitivity level (or vice versa) is often desirable because it directly targets the clinical utility of the intended clinical test. Meanwhile, covariates, such as age, race, as well as sample collection conditions, could impact the biomarker distribution and may also confound the association between biomarker and disease status. Therefore, covariate adjustment is important in such biomarker evaluation. Most existing covariate adjustment methods do not specifically target the desired sensitivity/specificity level, but rather do so for the entire biomarker distribution. As such, they might be more prone to model misspecification. In this paper, we suggest a parsimonious quantile regression model for the diseased population, only locally at the controlled sensitivity level, and assess specificity with covariate-specific control of the sensitivity. Variance estimates are obtained from a sample-based approach and bootstrap. Furthermore, our proposed local model extends readily to a global one for covariate adjustment for the receiver operating characteristic (ROC) curve over the sensitivity continuum. We demonstrate computational efficiency of this proposed method and restore the inherent monotonicity in the estimated covariate-adjusted ROC curve. The asymptotic properties of the proposed estimators are established. Simulation studies show favorable performance of the proposal. Finally, we illustrate our method in biomarker evaluation for aggressive prostate cancer.

show abstract

Section: Introductionmentioning

confidence: 99%

Covariate adjustment in continuous biomarker assessment

Huang

Patil

et al. 2021

Biometrics

View full text Add to dashboard Cite

show abstract

“…Clearly this approach is prohibitively expensive in computation. An alternative possibility is to consider Bayesian bootstrap similar to Inacio de Carvalho & Rodrìguez-Àlvarez 57 . However, it is not immediately clear how the strategy can be implemented in the framework of ordered ROC curves, and some new developments are needed to adequately solve the problem with reasonable computational costs.…”

Section: Discussionmentioning

confidence: 99%

Estimation of multiple ordered ROC curves using placement values

Ghosal

Grantz

Chen

2022

Stat Methods Med Res

View full text Add to dashboard Cite

In many diagnostic accuracy studies, a priori orders may be available on multiple receiver operating characteristic curves. For example, being closer to delivery, fetal ultrasound measures in the third trimester should be no less accurate than those in the second trimester in predicting small-for-gestational-age births. Such an a priori order should be incorporated in estimating receiver operating characteristic curves and associated summary accuracy statistics, as it can potentially improve statistical efficiency of these estimates. Early work in the literature has mainly taken an indirect approach to this task and has induced the desired a priori order through modeling test score distributions. We instead propose a new strategy that incorporates the order directly through the modeling of receiver operating characteristic curves. We achieve this by exploiting the link between placement value (the relative position of a diseased test score in the healthy score distribution), the cumulative distribution function of placement value, and receiver operating characteristic curve, and by building stochastically ordered random variables through mixture distributions. We take a Bayesian semiparametric approach in using Dirichlet process mixture models so that the placement values can be flexibly modeled. We conduct extensive simulation studies to examine the performance of the proposed methodology and apply the new framework to data from obstetrics and women’s health studies.

show abstract

“…Unadjusted receiver operator curves (ROC) were constructed and the area under the curve (AUC) was calculated to estimate the predictive power of the four steroid candidates for predicting delivery time. Covariate-adjusted ROC curves were obtained by the Nonparametric Bayesian model based on a single-weights-dependent Dirichlet process mixture of normal distributions and the Bayesian bootstrap [ 20 ]. The backward selection was used to remove predictors that were not significantly associated with delivery within 7 days (Wald statistic p ≥ .05) to obtain the final model.…”

Section: Methodsmentioning

confidence: 99%

Delivery prediction by quantitative analysis of four steroid metabolites with liquid chromatography tandem mass spectrometry in asymptomatic pregnant women

Meng

et al. 2022

Annals of Medicine

View full text Add to dashboard Cite

Background Prediction of delivery is important for assessing due dates, providing adequate prenatal care, and suggesting appropriate interventions in preterm and post-term pregnancies. Recent metabolomic findings suggested that the temporal abundance information of metabolome can be used to predict delivery timing with high accuracy in a cohort of healthy women. However, a targeted and quantitative assay is required to further validate the clinical performance and utility of this group of metabolomic candidates in delivery prediction with a larger and independent cohort. Method LC-MS/MS quantitative assays were applied to determine the plasma concentrations of four steroid metabolites, including oestriol-16-glucuronide (E3-16-Gluc), 17-alpha-hydroxyprogesterone (17-OHP), tetrahydrodeoxycorticosterone (THDOC), and androstane-3,17-diol (A-3,17-Diol) in asymptomatic women of singleton pregnancies (≥30 th gestational weeks). Subsequent statistical analysis was conducted to assess the performance of the above candidates in delivery prediction. Result Using LC-MS/MS, four steroids were separated and quantified in 5.5 min. The coefficients of variation (CVs) of the four analytes at the lower limit of quantification ranged from 7.9% to 14.6%, with the R 2 values greater than 0.990 in the calibration curves. Of the 585 recruited pregnant women who ended up with spontaneous delivery, 17.1% and 82.9% of the subjects delivered within and after 7 days since plasma collection, respectively. In the receiver operator curve analysis, the gestational age-adjusted area under the curve of the combined measurements of E3-16-Gluc and 17-OHP was 0.69 (95% CI: 0.60–0.76), with the sensitivity of 87.0% (95% CI: 78.8%–92.9%) and specificity of 60.2% (95% CI: 55.7%–64.6%). Moreover, the positive and the negative predictive values were 28.3%–34.0% and 93.1%–97.4% respectively for this combined panel. Conclusion We performed analytical and clinical validation of a quantitation LC-MS/MS panel for the four steroids in the plasma of pregnant women. The steroid metabolites panel of E3-16-Gluc and 17-OHP was potentially useful for predicting delivery within one week in asymptomatic women of singleton pregnancies. Key messages A quantitative LC-MS/MS assay for determining the plasma levels of 17-OHP, THDOC, A-3,17-Diol and E3-16-Gluc was developed and validated, in order to evaluate their predictive performance in asymptomatic delivery of singleton pregnancy. The levels of E3-16-Gluc and 17-OHP were found to be significantly elevated at the time of sampling in women that delivered within one week and their combinational testing may be potentially useful in delivery prediction.

show abstract

Bayesian Nonparametric Approaches for ROC Curve Inference

Cited by 10 publications

References 33 publications

Covariate adjustment in continuous biomarker assessment

Covariate adjustment in continuous biomarker assessment

Estimation of multiple ordered ROC curves using placement values

Delivery prediction by quantitative analysis of four steroid metabolites with liquid chromatography tandem mass spectrometry in asymptomatic pregnant women

Contact Info

Product

Resources

About