Determining the effects of LLD and MCI on brain decline according to machine learning and a structural covariance network analysis

Connectome-based schizophrenia prediction using structural connectivity - Deep Graph Neural Network(sc-DGNN)

Background

Connectome is understanding the complex organization of the human brain's structural and functional connectivity is essential for gaining insights into cognitive processes and disorders.

Objective

To improve the prediction accuracy of brain disorder issues, the current study investigates dysconnected subnetworks and graph structures associated with schizophrenia.

Method

By using the proposed structural connectivity-deep graph neural network (sc-DGNN) model and compared with machine learning (ML) and deep learning (DL) models.This work attempts to focus on eighty-eight subjects of diffusion magnetic resonance imaging (dMRI), three classical ML, and five DL models.

Result

The structural connectivity-deep graph neural network (sc-DGNN) model is proposed to effectively predict dysconnectedness associated with schizophrenia and exhibits superior performance compared to traditional ML and DL (GNNs) methods in terms of accuracy, sensitivity, specificity, precision, F1-score, and Area under receiver operating characteristic (AUC).

Conclusion

The classification task on schizophrenia using structural connectivity matrices and experimental results showed that linear discriminant analysis (LDA) performed 72% accuracy rate in ML models and sc-DGNN performed at a 93% accuracy rate in DL models to distinguish between schizophrenia and healthy patients.

Spatial navigation is associated with subcortical alterations and progression risk in subjective cognitive decline

BACKGROUND

Subjective cognitive decline (SCD) may serve as a symptomatic indicator for preclinical Alzheimer's disease; however, SCD is a heterogeneous entity regarding clinical progression. We aimed to investigate whether spatial navigation could reveal subcortical structural alterations and the risk of progression to objective cognitive impairment in SCD individuals.

METHODS

One hundred and eighty participants were enrolled: those with SCD (n = 80), normal controls (NCs, n = 77), and mild cognitive impairment (MCI, n = 23). SCD participants were further divided into the SCD-good (G-SCD, n = 40) group and the SCD-bad (B-SCD, n = 40) group according to their spatial navigation performance. Volumes of subcortical structures were calculated and compared among the four groups, including basal forebrain, thalamus, caudate, putamen, pallidum, hippocampus, amygdala, and accumbens. Topological properties of the subcortical structural covariance network were also calculated. With an interval of 1.5 years ± 12 months of follow-up, the progression rate to MCI was compared between the G-SCD and B-SCD groups.

RESULTS

Volumes of the basal forebrain, the right hippocampus, and their respective subfields differed significantly among the four groups (p < 0.05, false discovery rate corrected). The B-SCD group showed lower volumes in the basal forebrain than the G-SCD group, especially in the Ch4p and Ch4a-i subfields. Furthermore, the structural covariance network of the basal forebrain and right hippocampal subfields showed that the B-SCD group had a larger Lambda than the G-SCD group, which suggested weakened network integration in the B-SCD group. At follow-up, the B-SCD group had a significantly higher conversion rate to MCI than the G-SCD group.

CONCLUSION

Compared to SCD participants with good spatial navigation performance, SCD participants with bad performance showed lower volumes in the basal forebrain, a reorganized structural covariance network of subcortical nuclei, and an increased risk of progression to MCI. Our findings indicated that spatial navigation may have great potential to identify SCD subjects at higher risk of clinical progression, which may contribute to making more precise clinical decisions for SCD individuals who seek medical help.

Different Modular Organization Between Early Onset and Late Onset Depression: A Study Base on Granger Causality Analysis

Background: Modular organization reflects the activity patterns of our brain. Different disease states may lead to different activity patterns and clinical features. Early onset depression (EOD) and late onset depression (LOD) share the same clinical symptoms, but have different treatment strategies and prognosis. Thus, explored the modular organization of EOD and LOD might help us understand their pathogenesis.

Method: The study included 82 patients with late life depression (EOD 40, LOD 42) and 90 healthy controls. We evaluated the memory, executive function and processing speed and performed resting-stage functional MRI for all participants. We constructed a functional network based on Granger causality analysis and carried out modularity, normalized mutual information (NMI), Phi coefficient, within module degree z-score, and participation coefficient analyses for all the participants.

Result: The Granger function network analysis suggested that the functional modularity was different among the three groups (P_auc = 0.0300), and NMI analysis confirmed that the partition of EOD was different from that of LOD (P_auc = 0.0190). Rh.10d.ROI (polar frontal cortex) and Rh.IPS1.ROI (dorsal stream visual cortex) were shown to be the potential specific nodes in the modular assignment according to the Phi coefficient (P = 0.0002, P_fdr = 0.0744 & P = 0.0004, P_fdr = 0.0744).

Conclusion: This study reveal that the functional modularity and partition were different between EOD and LOD in Granger function network. These findings support the hypothesis that different pathological changes might exist in EOD and LOD.