Discriminating cognitive status in Parkinson’s disease through functional connectomics and machine learning

Abstract

There is growing interest in the potential of neuroimaging to help develop non-invasive biomarkers in neurodegenerative diseases. In this study, connection-wise patterns of functional connectivity were used to distinguish Parkinson’s disease patients according to cognitive status using machine learning. Two independent subject samples were assessed with resting-state fMRI. The first (training) sample comprised 38 healthy controls and 70 Parkinson’s disease patients (27 with mild cognitive impairment). The second (validation) sample included 25 patients (8 with mild cognitive impairment). The Brainnetome atlas was used to reconstruct the functional connectomes. Using a support vector machine trained on features selected through randomized logistic regression with leave-one-out cross-validation, a mean accuracy of 82.6% (p < 0.002) was achieved in separating patients with mild cognitive impairment from those without it in the training sample. The model trained on the whole training sample achieved an accuracy of 80.0% when used to classify the validation sample (p = 0.006). Correlation analyses showed that the connectivity level in the edges most consistently selected as features was associated with memory and executive function performance in the patient group. Our results demonstrate that connection-wise patterns of functional connectivity may be useful for discriminating Parkinson’s disease patients according to the presence of cognitive deficits.

Statistical inference in brain graphs using threshold‐free network‐based statistics

“…We initially generated a ground‐truth matrix containing a pattern of connections defined as “altered,” to be used in the simulated connectivity matrices. To make these ground‐truth effects reflect a somewhat realistic topology, we performed univariate comparisons between a sample of Parkinson's disease patients with mild cognitive impairment ( n = 27) and a group of healthy controls ( n = 38), seen in a previous study by our group to have significant resting‐state functional connectivity differences (Abós et al, ). Data acquisition and image preprocessing were identical to those used in that study.…”

“…One of the most frequently used edge‐wise methods is the network‐based statistic (NBS) (Zalesky et al, ). The NBS is designed to identify clustered effects in brain graphs, and has been used in different study settings (Abós et al, ; Cocchi et al, ; Conti et al, ; McColgan et al, ; Rigon, Voss, Turkstra, Mutlu, & Duff, ; Roberts et al, ). Specifically, the NBS is a technique that aims to identify connected components, consisting of neighboring edges that display statistical effects above a predetermined threshold (Zalesky et al, ).…”

Alterations in brain network organization in adults with obesity as compared to healthy-weight individuals and seniors

“…One sample comprised 32 non-obese healthy seniors (51-85 years old). The recruitment procedure of this group is fully described in Abós et al (2017). Briefly, exclusion criteria consisted on presence of psychiatric or neurological comorbidity, low global intelligence quotient estimated by the WAIS-III Vocabulary subtest score (> 7 scalar score) (Wechsler, 1999), and a Mini-Mental state examination score below 25 (Folstein, Folstein, & McHugh, 1975).…”

Detecting Abnormal Brain Regions in Schizophrenia Using Structural MRI via Machine Learning

“…e SVM is presently one of the best-known classification techniques and has computational advantages over other classification methods, and many previous studies [52][53][54][55][56] have proven that the linear SVM performs well in small sample datasets. To allow the classifier to generalize unseen data well and to avoid overfitting problems, we introduced the SVM soft margin classifier.…”