Interval estimation in three-class receiver operating characteristic analysis: A fairly general approach based on the empirical likelihood.

The empirical likelihood is a powerful nonparametric tool, that emulates its parametric counterpart-the parametric likelihood-preserving many of its large-sample properties. This article tackles the problem of assessing the discriminatory power of three-class diagnostic tests from an empirical likelihood perspective. In particular, we concentrate on interval estimation in a three-class receiver operating characteristic analysis, where a variety of inferential tasks could be of interest. We present novel theoretical results and tailored techniques studied to efficiently solve some of such tasks. Extensive simulation experiments are provided in a supporting role, with our novel proposals compared to existing competitors, when possible. It emerges that our new proposals are extremely flexible, being able to compete with contestants and appearing suited to accommodating several distributions, such, for example, mixtures, for target populations. We illustrate the application of the novel proposals with a real data example. The article ends with a discussion and a presentation of some directions for future research.

Receiver operating characteristic estimation and threshold selection criteria in three-class classification problems for clustered data.

Statistical evaluation of diagnostic tests, and, more generally, of biomarkers, is a constantly developing field, in which complexity of the assessment increases with the complexity of the design under which data are collected. One particularly prevalent type of data is clustered data, where individual units are naturally nested into clusters. In these cases, Bias can arise from omission, in the evaluation process, of cluster-level effects and/or individual covariates. Focusing on the three-class case and for continuous-valued diagnostic tests, we investigate how to exploit the clustered structure of data within a linear-mixed model approach, both when the assumption of normality holds and when it does not. We provide a method for the estimation of covariate-specific receiver operating characteristic surfaces and discuss methods for the choice of optimal thresholds, proposing three possible estimators. A proof of consistency and asymptotic normality of the proposed threshold estimators is given. All considered methods are evaluated by extensive simulation experiments. As an application, we study the use of the Lysosomal Associated Membrane Protein Family Member 5 gene expression as a biomarker to distinguish among three types of glutamatergic neurons.

Non-monotone transformation of biomarkers.

We comment here on a recent paper in this journal, on a non-monotone transformation of biomarkers aimed at improving diagnostic accuracy. We highlight that, in a binary classification problem, the proposed transformation finds its motivation in the Neyman-Pearson lemma, so that the underlying approach is very general and it is applicable to many parametric families, other than the normal one.

Relationship between Muscular Activity and Postural Control Changes after Proprioceptive Focal Stimulation (Equistasi®) in Middle-Moderate Parkinson's Disease Patients: An Explorative Study.

The aim of this study was to investigate the effects of Equistasi®, a wearable device, on the relationship between muscular activity and postural control changes in a sample of 25 Parkinson's disease (PD) subjects. Gait analysis was carried out through a six-cameras stereophotogrammetric system synchronized with two force plates, an eight-channel surface electromyographic system, recording the activity of four muscles bilaterally: Rectus femoris, tibialis anterior (TA), biceps femoris, and gastrocnemius lateralis (GL). The peak of the envelope (PoE) and its occurrence within the gait cycle (position of the peak of the envelope, PPoE) were calculated. Frequency-domain posturographic parameters were extracted while standing still on a force plate in eyes open and closed conditions for 60 s. After the treatment with Equistasi®, the mid-low (0.5-0.75) Hz and mid-high (0.75-1 Hz) components associated with the vestibular and somatosensory systems, PoE and PPoE, displayed a shift toward the values registered on the controls. Furthermore, a correlation was found between changes in proprioception (power spectrum frequencies during the Romberg Test) and the activity of GL, BF (PoE), and TA (PPoE). Results of this study could provide a quantitative estimation of the effects of a neurorehabilitation device on the peripheral and central nervous system in PD.

A pseudo-likelihood approach for multivariate meta-analysis of test accuracy studies with multiple thresholds.

Multivariate meta-analysis of test accuracy studies when tests are evaluated in terms of sensitivity and specificity at more than one threshold represents an effective way to synthesize results by fully exploiting the data, if compared to univariate meta-analyses performed at each threshold independently. The approximation of logit transformations of sensitivities and specificities at different thresholds through a normal multivariate random-effects model is a recent proposal that straightforwardly extends the bivariate models well recommended for the one threshold case. However, drawbacks of the approach, such as poor estimation of the within-study correlations between sensitivities and between specificities, and severe computational issues can make it unappealing. We propose an alternative method for inference on common diagnostic measures using a pseudo-likelihood constructed under a working independence assumption between sensitivities and between specificities at different thresholds in the same study. The method does not require within-study correlations, overcomes the convergence issues and can be effortlessly implemented. Simulation studies highlight a satisfactory performance of the method, remarkably improving the results from the multivariate normal counterpart under different scenarios. The pseudo-likelihood approach is illustrated in the evaluation of a test used for diagnosis of preeclampsia as a cause of maternal and perinatal morbidity and mortality.

bcROCsurface: an R package for correcting verification bias in estimation of the ROC surface and its volume for continuous diagnostic tests.

BACKGROUND: Receiver operating characteristic (ROC) surface analysis is usually employed to assess the accuracy of a medical diagnostic test when there are three ordered disease status (e.g. non-diseased, intermediate, diseased). In practice, verification bias can occur due to missingness of the true disease status and can lead to a distorted conclusion on diagnostic accuracy. In such situations, bias-corrected inference tools are required. RESULTS: This paper introduce an R package, named bcROCsurface, which provides utility functions for verification bias-corrected ROC surface analysis. The shiny web application of the correction for verification bias in estimation of the ROC surface analysis is also developed. CONCLUSION: bcROCsurface may become an important tool for the statistical evaluation of three-class diagnostic markers in presence of verification bias. The R package, readme and example data are available on CRAN. The web interface enables users less familiar with R to evaluate the accuracy of diagnostic tests, and can be found at http://khanhtoduc.shinyapps.io/bcROCsurface_shiny/ .