Classification of severe obstructive sleep apnea with cognitive impairment using degree centrality: A machine learning analysis

Abstract

In this study, we aimed to use voxel-level degree centrality (DC) features in combination with machine learning methods to distinguish obstructive sleep apnea (OSA) patients with and without mild cognitive impairment (MCI). Ninety-nine OSA patients were recruited for rs-MRI scanning, including 51 MCI patients and 48 participants with no mild cognitive impairment. Based on the Automated Anatomical Labeling (AAL) brain atlas, the DC features of all participants were calculated and extracted. Ten DC features were screened out by deleting variables with high pin-correlation and minimum absolute contraction and performing selective operator lasso regression. Finally, three machine learning methods were used to establish classification models. The support vector machine method had the best classification efficiency (AUC = 0.78), followed by random forest (AUC = 0.71) and logistic regression (AUC = 0.77). These findings demonstrate an effective machine learning approach for differentiating OSA patients with and without MCI and provide potential neuroimaging evidence for cognitive impairment caused by OSA.

Keywords: degree centrality; machine learning; mild cognitive impairment; obstructive sleep apnea; resting-state functional magnetic resonance imaging.

Figure 1

(A) The original rs-MRI was preprocessed and regions of interest were extracted by AAL template as features. (B–C) All the features extracted from DC were screened for feature correlation, and the minimum absolute contraction and Selection operator logic method was used for 10-fold cross verification to retain the features with non-zero coefficients. (D) The extracted features are trained by SVM, RF and LR to obtain the best model. (E) Visual mapping of brain regions according to the characteristics of the best model.

Figure 2

Red represents the default mode network; Blue represents the basal node network; Green represents the cerebellum network.

Figure 3

(A) The ROC curves of SVM models. (B) The ROC curves of RF models. (C) The ROC curves of LR models.