Examining stability of independent component analysis based on coefficient and component matrices for voxel-based morphometry of structural magnetic resonance imaging

Neuroimaging and natural language processing-based classification of suicidal thoughts in major depressive disorder

Suicide is a growing public health problem around the world. The most important risk factor for suicide is underlying psychiatric illness, especially depression. Detailed classification of suicide in patients with depression can greatly enhance personalized suicide control efforts. This study used unstructured psychiatric charts and brain magnetic resonance imaging (MRI) records from a psychiatric outpatient clinic to develop a machine learning-based suicidal thought classification model. The study included 152 patients with new depressive episodes for development and 58 patients from a geographically different hospital for validation. We developed an eXtreme Gradient Boosting (XGBoost)-based classification models according to the combined types of data: independent components-map weightings from brain T1-weighted MRI and topic probabilities from clinical notes. Specifically, we used 5 psychiatric symptom topics and 5 brain networks for models. Anxiety and somatic symptoms topics were significantly more common in the suicidal group, and there were group differences in the default mode and cortical midline networks. The clinical symptoms plus structural brain patterns model had the highest area under the receiver operating characteristic curve (0.794) versus the clinical notes only and brain MRI only models (0.748 and 0.738, respectively). The results were consistent across performance metrics and external validation. Our findings suggest that focusing on personalized neuroimaging and natural language processing variables improves evaluation of suicidal thoughts.

Explainable multimodal prediction of treatment-resistance in patients with depression leveraging brain morphometry and natural language processing

Although 20 % of patients with depression receiving treatment do not achieve remission, predicting treatment-resistant depression (TRD) remains challenging. In this study, we aimed to develop an explainable multimodal prediction model for TRD using structured electronic medical record data, brain morphometry, and natural language processing. In total, 247 patients with a new depressive episode were included. TRD-predictive models were developed based on the combination of following parameters: selected tabular dataset features, independent components-map weightings from brain T1-weighted magnetic resonance imaging (MRI), and topic probabilities from clinical notes. All models applied the extreme gradient boosting (XGBoost) algorithm via five-fold cross-validation. The model using all data sources showed the highest area under the receiver operating characteristic of 0.794, followed by models that used combined brain MRI and structured data, brain MRI and clinical notes, clinical notes and structured data, brain MRI only, structured data only, and clinical notes only (0.770, 0.762, 0.728, 0.703, 0.684, and 0.569, respectively). Classifications of TRD were driven by several predictors, such as previous exposure to antidepressants and antihypertensive medications, sensorimotor network, default mode network, and somatic symptoms. Our findings suggest that a combination of clinical data with neuroimaging and natural language processing variables improves the prediction of TRD.

Changes of brain function in patients with type 2 diabetes mellitus measured by different analysis methods: A new coordinate-based meta-analysis of neuroimaging

Objective

Neuroimaging meta-analysis identified abnormal neural activity alterations in patients with type 2 diabetes mellitus (T2DM), but there was no consistency or heterogeneity analysis between different brain imaging processing strategies. The aim of this meta-analysis was to determine consistent changes of regional brain functions in T2DM via the indicators obtained by using different post-processing methods.

Methods

Since the indicators obtained using varied post-processing methods reflect different neurophysiological and pathological characteristics, we further conducted a coordinate-based meta-analysis (CBMA) of the two categories of neuroimaging literature, which were grouped according to similar data processing methods: one group included regional homogeneity (ReHo), independent component analysis (ICA), and degree centrality (DC) studies, while the other group summarized the literature on amplitude of low-frequency fluctuation (ALFF) and cerebral blood flow (CBF).

Results

The final meta-analysis included 23 eligible trials with 27 data sets. Compared with the healthy control group, when neuroimaging studies were combined with ReHo, ICA, and DC measurements, the brain activity of the right Rolandic operculum, right supramarginal gyrus, and right superior temporal gyrus in T2DM patients decreased significantly. When neuroimaging studies were combined with ALFF and CBF measurements, there was no clear evidence of differences in the brain function between T2DM and HCs.

Conclusion

T2DM patients have a series of spontaneous abnormal brain activities, mainly involving brain regions related to learning, memory, and emotion, which provide early biomarkers for clarifying the mechanism of cognitive impairment and neuropsychiatric disorders in diabetes.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=247071, PROSPERO [CRD42021247071].

Brain age estimation using multi-feature-based networks

Studying brain aging improves our understanding in differentiating typical and atypical aging. Directly utilizing traditional morphological features for brain age estimation did not show significant performance in healthy controls (HCs), which may be due to the negligence of the information of structural similarities among cortical regions. For this issue, the multi-feature-based network (MFN) built upon morphological features can be employed to describe these similarities. Based on this, we hypothesized that the MFN is more efficient and robust than traditional morphological features in brain age estimating. In this work, we used six different types of morphological features (i.e., cortical volume, cortical thickness, curvature index, folding index, local gyrification index, and surface area) to build individual MFN for brain age estimation. The efficacy of MFN was estimated on 2501 HCs with T1-weighted structural magnetic resonance imaging (sMRI) data and compared with traditional morphological features. We attained a mean absolute error (MAE) of 3.73 years using the proposed method on an independent test set, whereas a mean absolute error of 5.30 years was derived from morphological features. Our experimental results demonstrated that the MFN is an efficient and robust metric for estimating brain age.

Dissociation Pattern in Default-Mode Network Homogeneity in Drug-Naive Bipolar Disorder

Default mode network (DMN) plays a key role in the pathophysiology of in bipolar disorder (BD). However, the homogeneity of this network in BD is still poorly understood. This study aimed to investigate abnormalities in the NH of the DMN at rest and the correlation between the NH of DMN and clinical variables in patients with BD. Forty drug-naive patients with BD and thirty-seven healthy control subjects participated in the study. Network homogeneity (NH) and independent component analysis (ICA) methods were used for data analysis. Support vector machines (SVM) method was used to analyze NH in different brain regions. Compared with healthy controls, significantly increased NH in the left superior medial prefrontal cortex (MPFC) and decreased NH in the right posterior cingulate cortex (PCC) and bilateral precuneus were found in patients with BD. NH in the right PCC was positively correlated with the verbal fluency test and verbal function total scores. NH in the left superior MPFC was negatively correlated with triglyceride (TG). NH in the right PCC was positively correlated with TG but negatively correlated with high-density lipoprotein cholesterol (HDL-C). NH in the bilateral precuneus was positively correlated with cholesterol and low-density lipoprotein cholesterol (LDL-C). In addition, NH in the left superior MPFC showed high sensitivity (80.00%), specificity (71.43%), and accuracy (75.61%) in the SVM results. These findings contribute new evidence of the participation of the altered NH of the DMN in the pathophysiology of BD.

Snowball ICA: A Model Order Free Independent Component Analysis Strategy for Functional Magnetic Resonance Imaging Data

In independent component analysis (ICA), the selection of model order (i.e., number of components to be extracted) has crucial effects on functional magnetic resonance imaging (fMRI) brain network analysis. Model order selection (MOS) algorithms have been used to determine the number of estimated components. However, simulations show that even when the model order equals the number of simulated signal sources, traditional ICA algorithms may misestimate the spatial maps of the signal sources. In principle, increasing model order will consider more potential information in the estimation, and should therefore produce more accurate results. However, this strategy may not work for fMRI because large-scale networks are widely spatially distributed and thus have increased mutual information with noise. As such, conventional ICA algorithms with high model orders may not extract these components at all. This conflict makes the selection of model order a problem. We present a new strategy for model order free ICA, called Snowball ICA, that obviates these issues. The algorithm collects all information for each network from fMRI data without the limitations of network scale. Using simulations and in vivo resting-state fMRI data, our results show that component estimation using Snowball ICA is more accurate than traditional ICA. The Snowball ICA software is available at https://github.com/GHu-DUT/Snowball-ICA.

Assessment of nonnegative matrix factorization algorithms for electroencephalography spectral analysis

BACKGROUND

Nonnegative matrix factorization (NMF) has been successfully used for electroencephalography (EEG) spectral analysis. Since NMF was proposed in the 1990s, many adaptive algorithms have been developed. However, the performance of their use in EEG data analysis has not been fully compared. Here, we provide a comparison of four NMF algorithms in terms of accuracy of estimation, stability (repeatability of the results) and time complexity of algorithms with simulated data. In the practical application of NMF algorithms, stability plays an important role, which was an emphasis in the comparison. A Hierarchical clustering algorithm was implemented to evaluate the stability of NMF algorithms.

RESULTS

In simulation-based comprehensive analysis of fit, stability, accuracy of estimation and time complexity, hierarchical alternating least squares (HALS) low-rank NMF algorithm (lraNMF_HALS) outperformed the other three NMF algorithms. In the application of lraNMF_HALS for real resting-state EEG data analysis, stable and interpretable features were extracted.

CONCLUSION

Based on the results of assessment, our recommendation is to use lraNMF_HALS, providing the most accurate and robust estimation.