Predicting Delayed Neurocognitive Recovery After Non-cardiac Surgery Using Resting-State Brain Network Patterns Combined With Machine Learning

Abstract

Delayed neurocognitive recovery (DNR) is a common subtype of postoperative neurocognitive disorders. An objective approach for identifying subjects at high risk of DNR is yet lacking. The present study aimed to predict DNR using the machine learning method based on multiple cognitive-related brain network features. A total of 74 elderly patients (≥ 60-years-old) undergoing non-cardiac surgery were subjected to resting-state functional magnetic resonance imaging (rs-fMRI) before the surgery. Seed-based whole-brain functional connectivity (FC) was analyzed with 18 regions of interest (ROIs) located in the default mode network (DMN), limbic network, salience network (SN), and central executive network (CEN). Multiple machine learning models (support vector machine, decision tree, and random forest) were constructed to recognize the DNR based on FC network features. The experiment has three parts, including performance comparison, feature screening, and parameter adjustment. Then, the model with the best predictive efficacy for DNR was identified. Finally, independent testing was conducted to validate the established predictive model. Compared to the non-DNR group, the DNR group exhibited aberrant whole-brain FC in seven ROIs, including the right posterior cingulate cortex, right medial prefrontal cortex, and left lateral parietal cortex in the DMN, the right insula in the SN, the left anterior prefrontal cortex in the CEN, and the left ventral hippocampus and left amygdala in the limbic network. The machine learning experimental results identified a random forest model combined with FC features of DMN and CEN as the best prediction model. The area under the curve was 0.958 (accuracy = 0.935, precision = 0.899, recall = 0.900, F1 = 0.890) on the test set. Thus, the current study indicated that the random forest machine learning model based on rs-FC features of DMN and CEN predicts the DNR following non-cardiac surgery, which could be beneficial to the early prevention of DNR.Clinical Trial Registration: The study was registered at the Chinese Clinical Trial Registry (Identification number: ChiCTR-DCD-15006096).

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

“…Our previous study found that patients with preoperative decreased FC between the bilateral MCC and left calcarine were more susceptible to DNR following surgery by logistic regression (Jiang et al, 2020). By exploring the whole-brain FC of key hubs in cognitive-related brain networks, we found that the altered whole-brain FC of DMN and central executive network could predict DNR in elderly patients using machine learning algorithms (Jiang et al, 2021). In addition, Wu et al (2021) established a machine learning DNR classification model based on the multi-order brain FC network features, achieving good prediction performance.…”

“…Written informed consent was obtained from all subjects participating in the trial before enrollment. The inclusion and exclusion criteria of our study population have been previously described (Jiang et al, 2020(Jiang et al, , 2021. The inclusion criteria were as follows: (1) patients scheduled to undergo non-cardiac surgery;…”

“…The neurocognitive tests consisted of MMSE, digit symbol substitution test (DSST), digit span forward and backward test (DSF/DSB), trail-making test-part A (TMT-A), and verbal fluency test (VFT). The Z score for each test and the composite Z score were calculated (Jiang et al, 2021). A patient was diagnosed with DNR when the Z scores of at least two of the neurocognitive tests or the composite Z score were ≥1.96.…”

“…The preprocessing of rs-fMRI data consisted of eight following steps, where the first step included discarding the first five volumes to avoid the potential noise related to the participants' adaptation to the scanner. Then, the remaining volumes were subjected to the slice-timing correction, head motion correction, spatial normalization, smoothing with a 6 × 6 × 6 mm Gaussian kernel, low-frequency filtering (0.01-0.08 Hz), linear trend of time course removal, and nuisance covariates regression (motion artifact, white matter signal, and cerebrospinal fluid signal; Jiang et al, 2021).…”

Novel Bedside Dynamic Nomograms to Predict the Probability of Postoperative Cognitive Dysfunction in Elderly Patients Undergoing Noncardiac Surgery: A Retrospective Study

“…[23][24][25][26][27] Unfortunately, few studies have established predictive models for neurocognitive impairment after non-cardiac surgery. [28][29][30] Hence, in this study, we aimed to develop the preoperative and postoperative models and establish bedside nomograms to provide an individualized prediction of POCD in elderly patients undergoing non-cardiac surgery.…”