Proton pump inhibitor effect on esophageal protein signature of eosinophilic esophagitis, prediction, and evaluation of treatment response.

BACKGROUND: Recently, we have identified a dysregulated protein signature in the esophageal epithelium of eosinophilic esophagitis (EoE) patients including proteins associated with inflammation and epithelial barrier function; however, the effect of proton pump inhibitor (PPI) treatment on this signature is unknown. Herein, we used a proteomic approach to investigate: (1) whether PPI treatment alters the esophageal epithelium protein profile observed in EoE patients and (2) whether the protein signature at baseline predicts PPI response. METHODS: We evaluated the protein signature of esophageal biopsies using a cohort of adult EoE (n = 25) patients and healthy controls (C) (n = 10). In EoE patients, esophageal biopsies were taken before (pre) and after (post) an 8-week PPI treatment, determining the histologic response. Eosinophil count PostPPI was used to classify the patients: ≥15 eosinophils/hpf as non-responders (non-responder) and < 15 eosinophils/hpf as responders (R). Protein signature was determined and differentially accumulated proteins were characterized to identify altered biological processes and signaling pathways. RESULTS: Comparative analysis of differentially accumulated proteins between groups revealed common signatures between three groups of patients with inflammation (responder-PrePPI, non-responder-PrePPI, and non-responder-PostPPI) and without inflammation (controls and responder-PostPPI). PPI therapy almost reversed the EoE specific esophageal protein signature, which is enriched in pathways associated with inflammation and epithelial barrier function, in responder-PostPPI. Furthermore, we identified a set of candidate proteins to differentiate responder-PrePPI and non-responder-PrePPI EoE patients before treatment. CONCLUSION: These findings provide evidence that PPI therapy reverses the alterations in esophageal inflammatory and epithelial proteins characterizing EoE, thereby providing new insights into the mechanism of PPI clinical response. Interestingly, our results also suggest that PPI response could be predicted at baseline in EoE.

Enhanced network synchronization connectivity following transcranial direct current stimulation (tDCS) in bipolar depression: Effects on EEG oscillations and deep learning-based predictors of clinical remission.

AIM: To investigate oscillatory networks in bipolar depression, effects of a home-based tDCS treatment protocol, and potential predictors of clinical response. METHODS: 20 participants (14 women) with bipolar disorder, mean age 50.75 ±â€¯10.46 years, in a depressive episode of severe severity (mean Montgomery-Åsberg Rating Scale (MADRS) score 24.60 ±â€¯2.87) received home-based transcranial direct current stimulation (tDCS) treatment for 6 weeks. Clinical remission defined as MADRS score < 10. Resting-state EEG data were acquired at baseline, prior to the start of treatment, and at the end of treatment, using a portable 4-channel EEG device (electrode positions: AF7, AF8, TP9, TP10). EEG band power was extracted for each electrode and phase locking value (PLV) was computed as a functional connectivity measure of phase synchronization. Deep learning was applied to pre-treatment PLV features to examine potential predictors of clinical remission. RESULTS: Following treatment, 11 participants (9 women) attained clinical remission. A significant positive correlation was observed with improvements in depressive symptoms and delta band PLV in frontal and temporoparietal regional channel pairs. An interaction effect in network synchronization was observed in beta band PLV in temporoparietal regions, in which participants who attained clinical remission showed increased synchronization following tDCS treatment, which was decreased in participants who did not achieve clinical remission. Main effects of clinical remission status were observed in several PLV bands: clinical remission following tDCS treatment was associated with increased PLV in frontal and temporal regions and in several frequency bands, including delta, theta, alpha and beta, as compared to participants who did not achieve clinical remission. The highest deep learning prediction accuracy 69.45 % (sensitivity 71.68 %, specificity 66.72 %) was obtained from PLV features combined from theta, beta, and gamma bands. CONCLUSIONS: tDCS treatment enhances network synchronization, potentially increasing inhibitory control, which underscores improvement in depressive symptoms. Baseline EEG-based measures might aid predicting clinical response.

Machine learning approaches and non-linear processing of extracted components in frontal region to predict rTMS treatment response in major depressive disorder.

Predicting the therapeutic result of repetitive transcranial magnetic stimulation (rTMS) treatment could save time and costs as ineffective treatment can be avoided. To this end, we presented a machine-learning-based strategy for classifying patients with major depression disorder (MDD) into responders (R) and nonresponders (NR) to rTMS treatment. Resting state EEG data were recorded using 32 electrodes from 88 MDD patients before treatment. Then, patients underwent 7 weeks of rTMS, and 46 of them responded to treatment. By applying Independent Component Analysis (ICA) on EEG, we identified the relevant brain sources as possible indicators of neural activity in the dorsolateral prefrontal cortex (DLPFC). This was served through estimating the generators of activity in the sensor domain. Subsequently, we added physiological information and placed certain terms and conditions to offer a far more realistic estimation than the classic EEG. Ultimately, those components mapped in accordance with the region of the DLPFC in the sensor domain were chosen. Features extracted from the relevant ICs time series included permutation entropy (PE), fractal dimension (FD), Lempel-Ziv Complexity (LZC), power spectral density, correlation dimension (CD), features based on bispectrum, frontal and prefrontal cordance, and a combination of them. The most relevant features were selected by a Genetic Algorithm (GA). For classifying two groups of R and NR, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) were applied to predict rTMS treatment response. To evaluate the performance of classifiers, a 10-fold cross-validation method was employed. A statistical test was used to assess the capability of features in differentiating R and NR for further research. EEG characteristics that can predict rTMS treatment response were discovered. The strongest discriminative indicators were EEG beta power, the sum of bispectrum diagonal elements in delta and beta bands, and CD. The Combined feature vector classified R and NR with a high performance of 94.31% accuracy, 92.85% specificity, 95.65% sensitivity, and 92.85% precision using SVM. This result indicates that our proposed method with power and nonlinear and bispectral features from relevant ICs time-series can predict the treatment outcome of rTMS for MDD patients only by one session pretreatment EEG recording. The obtained results show that the proposed method outperforms previous methods.

Prediction of rTMS treatment response in major depressive disorder using machine learning techniques and nonlinear features of EEG signal.

BACKGROUND: Prediction of therapeutic outcome of repetitive transcranial magnetic stimulation (rTMS) treatment is an important purpose that eliminates financial and psychological consequences of applying inefficient therapy. To achieve this goal we proposed a method based on machine learning to classify responders (R) and non- responders (NR) to rTMS treatment for major depression disorder (MDD) patients. METHODS: 19 electrodes resting state EEG was recorded from 46 MDD patients before treatment. Then patients underwent 7 weeks of rTMS, and 23 of them responded to treatment. Features extracted from EEG include Lempel-Ziv complexity (LZC), Katz fractal dimension (KFD), correlation dimension (CD), the power spectral density, features based on bispectrum, frontal and prefrontal cordance and combination of them. The most relevant features were selected by the minimal-redundancy-maximal-relevance (mRMR) feature selection algorithm. For classifying two groups of R and NR, k-nearest neighbors (KNN) were applied. The performance of the proposed method was evaluated by leave-1-out cross-validation. For further study, the capability of features in differentiating R and NR was investigated by a statistical test. RESULTS: Effective EEG features for prediction of rTMS treatment response were found. EEG beta power, the sum of bispectrum diagonal elements in delta and beta bands and CD were the most discriminative features. Power of beta classified R and NR with the high performance of 91.3% accuracy, 91.3% specificity, and 91.3% sensitivity. LIMITATIONS: Lack of large sample size restricted our method for using in clinical applications. CONCLUSION: This considerable high accuracy indicates that our proposed method with power and some of the nonlinear and bispectral features can lead to promising results in predicting treatment outcome of rTMS for MDD patients only by one session pretreatment EEG recording.