Multi-Order Brain Functional Connectivity Network-Based Machine Learning Method for Recognition of Delayed Neurocognitive Recovery in Older Adults Undergoing Non-cardiac Surgery.

Guoqing Wu,Xixue Zhang,Shihong Li,Zhijun Bao,Guangwu Lin,Zhaoshun Jiang,Songbin Liu,Yuxi Cai,Weidong Gu,Yating Lv

doi:10.3389/fnins.2021.707944

Guoqing Wu, Xixue Zhang + Show 8 more

Open Access

https://doi.org/10.3389/fnins.2021.707944

Copy DOI

Abstract

Objectives: Delayed neurocognitive recovery (DNR) seriously affects the post-operative recovery of elderly surgical patients, but there is still a lack of effective methods to recognize high-risk patients with DNR. This study proposed a machine learning method based on a multi-order brain functional connectivity (FC) network to recognize DNR.Method: Seventy-four patients who completed assessments were included in this study, in which 16/74 (21.6%) had DNR following surgery. Based on resting-state functional magnetic resonance imaging (rs-fMRI), we first constructed low-order FC networks of 90 brain regions by calculating the correlation of brain region signal changing in the time dimension. Then, we established high-order FC networks by calculating correlations among each pair of brain regions. Afterward, we built sparse representation-based machine learning model to recognize DNR on the extracted multi-order FC network features. Finally, an independent testing was conducted to validate the established recognition model.Results: Three hundred ninety features of FC networks were finally extracted to identify DNR. After performing the independent-sample T test between these features and the categories, 15 features showed statistical differences (P < 0.05) and 3 features had significant statistical differences (P < 0.01). By comparing DNR and non-DNR patients’ brain region connection matrices, it is found that there are more connections among brain regions in DNR patients than in non-DNR patients. For the machine learning recognition model based on multi-feature combination, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the classifier reached 95.61, 92.00, 66.67, and 100.00%, respectively.Conclusion: This study not only reveals the significance of preoperative rs-fMRI in recognizing post-operative DNR in elderly patients but also establishes a promising machine learning method to recognize DNR.

Highlights

The neurocognitive impairment including memory, information processing, and execution identified from 7 to 30 days post-operatively is defined as delayed neurocognitive recovery (DNR) (Berger et al, 2015; Evered et al, 2018)
Seventy-four patients who completed both preoperative and post-operative MRI scans and all neuropsychological tests were used for the final experimental analysis. Among these 74 patients, 16 cases were diagnosed as DNR and 58 cases were diagnosed as non-DNR
The education order of DNR patients was significantly lower than that of non-DNR patients, while in terms of age, gender, height, weight, and obesity, there was no difference between the two groups of patients

Summary

Introduction

The neurocognitive impairment including memory, information processing, and execution identified from 7 to 30 days post-operatively is defined as delayed neurocognitive recovery (DNR) (Berger et al, 2015; Evered et al, 2018). Jiang et al (2020) found that the preoperative higher amplitude of low-frequency fluctuation (ALFF) in the bilateral middle cingulate cortex (MCC) and lower functional connectivity (FC) between the bilateral MCC and left calcarine were independently associated with the occurrence of DNR. These studies have identified possible preoperative neuroimaging risk factors for DNR, the correlation between different factors was not further considered in the research process, and a stable and reliable DNR patient recognition model based on those factors has not been established

Objectives

Methods

Results