Quantitative Identification of Functional Connectivity Disturbances in Neuropsychiatric Lupus Based on Resting-State fMRI: A Robust Machine Learning Approach.

Nicholas John Simos,Panagiotis Simos,George Bertsias,Georgios C Manikis,Eleftherios Kavroulakis,Thomas G Maris,Stavros I Dimitriadis,Efrosini Papadaki

doi:10.3390/brainsci10110777

Abstract

Neuropsychiatric systemic lupus erythematosus (NPSLE) is an autoimmune entity comprised of heterogenous syndromes affecting both the peripheral and central nervous system. Research on the pathophysiological substrate of NPSLE manifestations, including functional neuroimaging studies, is extremely limited. The present study examined person-specific patterns of whole-brain functional connectivity in NPSLE patients (n = 44) and age-matched healthy control participants (n = 39). Static functional connectivity graphs were calculated comprised of connection strengths between 90 brain regions. These connections were subsequently filtered through rigorous surrogate analysis, a technique borrowed from physics, novel to neuroimaging. Next, global as well as nodal network metrics were estimated for each individual functional brain network and were input to a robust machine learning algorithm consisting of a random forest feature selection and nested cross-validation strategy. The proposed pipeline is data-driven in its entirety, and several tests were performed in order to ensure model robustness. The best-fitting model utilizing nodal graph metrics for 11 brain regions was associated with 73.5% accuracy (74.5% sensitivity and 73% specificity) in discriminating NPSLE from healthy individuals with adequate statistical power. Closer inspection of graph metric values suggested an increased role within the functional brain network in NSPLE (indicated by higher nodal degree, local efficiency, betweenness centrality, or eigenvalue efficiency) as compared to healthy controls for seven brain regions and a reduced role for four areas. These findings corroborate earlier work regarding hemodynamic disturbances in these brain regions in NPSLE. The validity of the results is further supported by significant associations of certain selected graph metrics with accumulated organ damage incurred by lupus, with visuomotor performance and mental flexibility scores obtained independently from NPSLE patients.

Highlights

Resting-state functional MRI is a non-invasive functional neuroimaging modality based on the blood-oxygen-level-dependent (BOLD) signal
We propose a robust automated machine learning (AutoML) approach based on individualized static functional connectivity graphs with the goal of defining objective connectomic biomarkers related to Neuropsychiatric systemic lupus erythematosus (NPSLE)
Based on the adopted Type I and II error levels (0.05–0.10), our findings are significant with 30 positive cases (NPSLE subjects) and 27 negative cases in a total sample size of 57 subjects compared to 83 subjects in both groups

Summary

Introduction

Resting-state functional MRI (rs-fMRI) is a non-invasive functional neuroimaging modality based on the blood-oxygen-level-dependent (BOLD) signal. Rs-fMRI can capture the intrinsic, innate or “default” processes, self-referential thought and introspection that are active even while subjects are at rest. This poses several challenges in experimental design, especially in appropriate analysis methodology. This is different from task-related functional neuroimaging studies, where several proposed methodologies attempt to identify patterns that in some form correspond to or correlate with the task or experiment performed during the examination. Useful and possibly novel biomarkers can emerge from state-of-the-art rs-fMRI analyses, further enhancing the understanding and interpretation of certain diseases, conditions, pathologies or neural processes

Objectives

Results

Discussion

Conclusion