Development and validation of a multimodal neuroimaging biomarker for electroconvulsive therapy outcome in depression: a multicenter machine learning analysis

Current approaches to studying human resting-state function in inflammatory bowel disease

Crohn's disease and ulcerative colitis are 2 subtypes of Inflammatory Bowel Disease (IBD). The chronic, alternating periods of relapsing, and remitting inflammation of the gastrointestinal tract that underlie these diseases trigger a range of gut-related symptoms, in addition to being related to burdensome psychological and cognitive comorbidities. With advancing knowledge of the brain-gut axis and its dysregulation in diseases such as IBD, understanding IBD-related brain changes is an important focus for current research in this area. "Resting state" function refers to the spontaneous fluctuations in neural activity when a person is awake and resting-not focussing attention on a task or stimulus. The recent surge in human resting-state functional magnetic resonance imaging (rs-fMRI) studies suggest that resting function is altered in IBD, representing a potential neural biomarker to target in the development of novel interventions. There are, however, multiple factors that contribute to the approach of these studies, including factors related to participant sample characteristics (IBD subtype and incorporation of disease activity in group definition and comparison), application of different resting-state metrics to assess resting brain activity (via regional homogeneity or amplitude of low-frequency fluctuations) or functional connectivity (via independent component analysis, region-of-interest, seed-to-voxel, or graph theory analyses) and incorporation of additional, multimodal variables of interest. The present review provides a summary of current approaches to studying resting-state brain function in IBD, the most commonly identified brain regions/networks to exhibit aberrant function, and avenues for advancement that forthcoming research in this field can strive to address.

Application of functional near-infrared spectroscopy and machine learning to predict treatment response after six months in major depressive disorder

Depression treatment responses vary widely among individuals. Identifying objective biomarkers with predictive accuracy for therapeutic outcomes can enhance treatment efficiency and avoid ineffective therapies. This study investigates whether functional near-infrared spectroscopy (fNIRS) and clinical assessment information can predict treatment response in major depressive disorder (MDD) through machine-learning techniques. Seventy patients with MDD were included in this 6-month longitudinal study, with the primary treatment outcome measured by changes in the Hamilton Depression Rating Scale (HAM-D) scores. fNIRS and clinical information were strictly evaluated using nested cross-validation to predict responders and non-responders based on machine-learning models, including support vector machine, random forest, XGBoost, discriminant analysis, Naïve Bayes, and transformers. The task change of total haemoglobin (HbT), defined as the difference between pre-task and post-task average HbT concentrations, in the dorsolateral prefrontal cortex (dlPFC) is significantly correlated with treatment response (p < 0.005). Leveraging a Naïve Bayes model, inner cross-validation performance (bAcc = 70% [SD = 4], AUC = 0.77 [SD = 0.04]) and outer cross-validation results (bAcc = 73% [SD = 3], AUC = 0.77 [SD = 0.02]) were yielded for predicting response using solely fNIRS data. The bimodal model combining fNIRS and clinical data showed inferior performance in outer cross-validation (bAcc = 68%, AUC = 0.70) compared to the fNIRS-only model. Collectively, fNIRS holds potential as a scalable neuroimaging modality for predicting treatment response in MDD.

A prediction model for electroconvulsive therapy effectiveness in patients with major depressive disorder from the Dutch ECT Consortium (DEC)

Reliable predictors for electroconvulsive therapy (ECT) effectiveness would allow a more precise and personalized approach for the treatment of major depressive disorder (MDD). Prediction models were created using a priori selected clinical variables based on previous meta-analyses. Multivariable linear regression analysis was used, applying backwards selection to determine predictor variables while allowing non-linear relations, to develop a prediction model for depression outcome post-ECT (and logistic regression for remission and response as secondary outcome measures). Internal validation and internal-external cross-validation were used to examine overfitting and generalizability of the model's predictive performance. In total, 1892 adult patients with MDD were included from 22 clinical and research cohorts of the twelve sites within the Dutch ECT Consortium. The final primary prediction model showed several factors that significantly predicted a lower depression score post-ECT: higher age, shorter duration of the current depressive episode, severe MDD with psychotic features, lower level of previous antidepressant resistance in the current episode, higher pre-ECT global cognitive functioning, absence of a comorbid personality disorder, and a lower level of failed psychotherapy in the current episode. The optimism-adjusted R² of the final model was 19%. This prediction model based on readily available clinical information can reduce uncertainty of ECT outcomes and hereby inform clinical decision-making, as prompt referral for ECT may be particularly beneficial for individuals with the above-mentioned characteristics. However, despite including a large number of pretreatment factors, a large proportion of the variance in depression outcome post-ECT remained unpredictable.

Longitudinal resting-state network connectivity changes in electroconvulsive therapy patients compared to healthy controls

OBJECTIVE

Electroconvulsive therapy (ECT) is effective for major depressive episodes. Understanding of underlying mechanisms has been increased by examining changes of brain connectivity but studies often do not correct for test-retest variability in healthy controls (HC). In this study, we investigated changes in resting-state networks after ECT in a multicenter study.

METHODS

Functional resting-state magnetic resonance imaging data, acquired before start and within one week after ECT, from 90 depressed patients were analyzed, as well as longitudinal data of 24 HC. Group-information guided independent component analysis (GIG-ICA) was used to spatially restrict decomposition to twelve canonical resting-state networks. Selected networks of interest were the default mode network (DMN), salience network (SN), and left and right frontoparietal network (LFPN, and RFPN). Whole-brain voxel-wise analyses were used to assess group differences at baseline, group by time interactions, and correlations with treatment effectiveness. In addition, between-network connectivity and within-network strengths were computed.

RESULTS

Within-network strength of the DMN was lower at baseline in ECT patients which increased after ECT compared to HC, after which no differences were detected. At baseline, ECT patients showed lower whole-brain voxel-wise DMN connectivity in the precuneus. Increase of within-network strength of the LFPN was correlated with treatment effectiveness. We did not find whole-brain voxel-wise or between-network changes.

CONCLUSION

DMN within-network connectivity normalized after ECT. Within-network increase of the LFPN in ECT patients was correlated with higher treatment effectiveness. In contrast to earlier studies, we found no whole-brain voxel-wise changes, which highlights the necessity to account for test-retest effects.

Electroconvulsive Therapy (ECT) in Major Depression: Oldies but Goodies

Electroconvulsive therapy is one of the useful treatment methods for symptom improvement and remission in patients with treatment-resistant depression. Considering the various clinical characteristics of patients experiencing depression, key indicators are extracted from structural brain magnetic resonance imaging, functional brain magnetic resonance imaging, and electroencephalography (EEG) data taken before treatment, and applied as explanatory variables in machine learning and network analysis. Studies that attempt to make reliable predictions about the degree of response to electroconvulsive treatment and the possibility of remission in patients with treatment-resistant depression are continuously being published. In addition, studies are being conducted to identify the correlation with clinical improvement by taking structural-functional brain magnetic resonance imaging after electroconvulsive therapy in depressed patients. By reviewing and integrating the results of the latest studies on the above matters, we aim to present the usefulness of electroconvulsive therapy for improving the personalized prognosis of patients with treatment-resistant depression.

Alterations of dynamic and static brain functional activities and integration in stroke patients

Objective

The study aimed to investigate the comprehensive characteristics of brain functional activity and integration in patients with subcortical stroke using dynamic and static analysis methods and to examine whether alterations in brain functional activity and integration were associated with clinical symptoms of patients.

Methods

Dynamic amplitude of low-frequency fluctuation (dALFF), static amplitude of low-frequency fluctuation (sALFF), dynamic degree centrality (dDC), and static degree centrality (sDC) were calculated for 19 patients with right subcortical stroke, 16 patients with left subcortical stroke, and 25 healthy controls (HC). Furthermore, correlation analysis was performed to investigate the relationships between changes in brain functional measurements of patients and clinical variables.

Results

Group comparison results showed that significantly decreased dALFF in the left angular (ANG_L) and right inferior parietal gyrus (IPG_R), decreased sALFF in the left precuneus (PCUN_L), and decreased sDC in the left crus II of cerebellar hemisphere (CERCRU2_L) and IPG_R, while significantly increased sDC in the right lobule X of cerebellar hemisphere (CER10_R) were detected in patients with right subcortical stroke relative to HC. Patients with left subcortical stroke showed significantly decreased sALFF in the left precuneus (PCUN_L) but increased sDC in the right hippocampus (HIP_R) compared with HC. Additionally, the altered sDC values in the CER10_R of patients with right subcortical stroke and in the HIP_R of patients with left subcortical stroke were associated with the severity of stroke and lower extremities motor function. A correlation was also found between the altered sALFF values in the PCUN_L of patients with left subcortical stroke and lower extremities motor function.

Conclusion

These findings suggest that time-varying brain activity analysis may supply complementary information for static brain activity analysis. Dynamic and static brain functional activity and integration analysis may contribute to a more comprehensive understanding of the underlying neuropathology of dysfunction in stroke patients.