Decreased default mode network functional connectivity with visual processing regions as potential biomarkers for delayed neurocognitive recovery - A resting-state fMRI study and machine-learning analysis

Aug 5, 2026

Upload by Jiven

Abnormal functional connectivity patterns within the default mode network are investigated as early indicators for delayed neurocognitive recovery after non-cardiac surgery. Resting-state fMRI performed before surgery in 74 patients is used to extract seed-based whole-brain connectivity features across 18 core DMN regions. Features with statistically significant differences between DNR and non-DNR groups are then fed into multiple machine-learning models, followed by independent testing and permutation-based performance evaluation. Results highlight decreased DMN connectivity with visual processing regions as predictive biomarkers.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Objectives

Methods

Results

Conclusion

Keywords

Introduction

TYPE Original Research PUBLISHED 06 January 2023 DOI 10.3389/fnagi.2022.1109485 OPEN ACCESS EDITED BY Hong Hai Zhang, Zhejiang University School of Medicine, China REVIEWED BY Yao Lu, First Affiliated Hospital of Anhui Medical University, China Weidong Yao, Wannan Medical College, China Kai Mo, Southern Medical University, China *CORRESPONDENCE Weidong Gu [hdmz0800@163.com](hdmz0800@163.com)[ ](hdmz0800@163.com)Shengdong Nie [nsd4647@163.com](nsd4647@163.com) †These authors have contributed equally to this work SPECIALTY SECTION This article was submitted to Neurocognitive Aging and Behavior, a section of the journal Frontiers in Aging Neuroscience RECEIVED 27 November 2022 ACCEPTED 16 December 2022 PUBLISHED 06 January 2023 CITATION Jiang Z, Cai Y, Liu S, Ye P, Yang Y, Lin G, Li S, Xu Y, Zheng Y, Bao Z, Nie S and Gu W (2023) Decreased default mode network functional connectivity with visual processing regions as potential biomarkers for delayed neurocognitive recovery: A resting-state fMRI study and machinelearning analysis. Front. Aging Neurosci. 14:1109485 . doi: 10.3389/fnagi.2022.1109485 COPYRIGHT © 2023 Jiang, Cai, Liu, Ye, Yang, Lin, Li, Xu, Zheng, Bao, Nie and Gu. This is an openaccess article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Decreased default mode network functional connectivity with visual processing regions as potential biomarkers for delayed neurocognitive recovery: A resting-state fMRI study and machine-learning analysis Zhaoshun Jiang 1, 2†, Yuxi Cai 1, 2†, Songbin Liu 1, 2, Pei Ye 1, 2, Yifeng Yang3, Guangwu Lin4, Shihong Li4, Yan Xu 1, Yangjing Zheng 1, Zhijun Bao 2, 5, 6, Shengdong Nie3* and Weidong Gu 1, 2* 1 Department of Anesthesiology, Huadong Hospital Affiliated to Fudan University, Shanghai, China, 2Shanghai Key Laboratory of Clinical Geriatric Medicine, Huadong Hospital Affiliated to Fudan University, Shanghai, China, 3School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China, 4 Department of Radiology, Huadong Hospital Affiliated to Fudan University, Shanghai, China, 5 Department of Geriatric Medicine, Huadong Hospital Affiliated to Fudan University, Shanghai, China, 6 Research Center on Aging and Medicine, Fudan University, Shanghai, China Objectives: The abnormal functional connectivity (FC) pattern of default mode network (DMN) may be key markers for early identification of various cognitive disorders. However, the whole-brain FC changes of DMN in delayed neurocognitive recovery (DNR) are still unclear. Our study was aimed at exploring the whole-brain FC patterns of all regions in DMN and the potential features as biomarkers for the prediction of DNR using machine-learning algorithms. Methods: Resting-state functional magnetic resonance imaging (fMRI) was conducted before surgery on 74 patients undergoing non-cardiac surgery. Seed-based whole-brain FC with 18 core regions located in the DMN was performed, and FC features that were statistically different between the DNR and non-DNR patients after false discovery correction were extracted. Afterward, based on the extracted FC features, machine-learning algorithms such as support vector machine, logistic regression, decision tree, and random forest were established to recognize DNR. The machine learning experiment procedure mainly included three following steps: feature standardization, parameter adjustment, and performance comparison. Finally, independent testing was conducted to validate the established prediction model. The algorithm performance was e

FAQs

What is the main objective of the study?

To identify whole-brain functional connectivity patterns of the default mode network and determine potential biomarker features for predicting delayed neurocognitive recovery using machine-learning algorithms.

How were DNR-related features extracted?

Resting-state fMRI before surgery was analyzed with seed-based whole-brain functional connectivity using 18 core DMN regions, and connectivity features differing between DNR and non-DNR patients were extracted after false discovery correction.

Which model performed best and what was its key outcome?

Random forest using 20 decision trees achieved the best result, with accuracy 84.0%, sensitivity 63.1%, specificity 89.5%, and an AUC of 86.4%. The most influential feature was connectivity between the left retrosplenial cortex/posterior cingulate cortex and the left precuneus.

Aug 5, 2026

Upload by Jiven