A Brainnetome Atlas Based Mild Cognitive Impairment Identification Using Hurst Exponent.

Area of Science:

• Neuroscience
• Medical Imaging
• Machine Learning

Background:

• Mild cognitive impairment (MCI) is a transitional stage between normal aging and Alzheimer's disease (AD), necessitating early detection for effective treatment.
• Current methods for identifying MCI require enhancement to facilitate timely clinical intervention and prevent irreversible brain damage.
• Functional magnetic resonance imaging (fMRI) offers insights into brain activity but requires sophisticated analysis for detecting subtle changes associated with MCI.

Purpose of the Study:

• To evaluate the efficacy of the Hurst exponent (HE) derived from fMRI data as a biomarker for identifying mild cognitive impairment (MCI).
• To develop and validate a machine learning algorithm for MCI classification using HE values.
• To identify specific brain regions exhibiting abnormal HE in individuals with MCI.

Main Methods:

• Range scaled analysis was employed to compute the Hurst exponent (HE) at a voxel level from fMRI data of 64 MCI patients and 60 healthy controls (HCs).
• Average HE values were extracted from regions of interest (ROIs) within the brainnetome atlas and compared between MCI and HC groups.
• A support vector machine (SVM) algorithm utilized abnormal average HE values as classification features, with performance assessed via leave-one-out cross-validation (LOOCV).

Main Results:

• The HE-based SVM algorithm achieved a classification accuracy of 83.1%, with 82.8% sensitivity and 83.3% specificity.
• The area under the receiver operating characteristic curve (AUC) was 0.88, indicating strong discriminative power.
• Abnormal HE values in MCI patients were predominantly observed in the left middle frontal gyrus, right hippocampus, bilateral parahippocampal gyrus, bilateral amygdala, left cingulate gyrus, left insular gyrus, left fusiform gyrus, left superior parietal gyrus, left orbital gyrus, and left basal ganglia.

Conclusions:

• The Hurst exponent (HE) is a promising and effective feature for the identification of mild cognitive impairment (MCI) using fMRI data.
• The developed SVM-based algorithm demonstrates significant potential for clinical application in early MCI detection.
• Identifying specific brain regions with abnormal HE provides valuable insights into the neurobiological underpinnings of MCI.