Predicting Symptomatic and Functional Improvements over 1 Year in Patients with First-Episode Psychosis Using Resting-State Electroencephalography

In perspective of specific symptoms of major depressive disorder: Functional connectivity analysis of electroencephalography and potential biomarkers of treatment response

BACKGROUND

The symptom variability in major depressive disorder (MDD) complicates treatment assessment, necessitating a thorough understanding of MDD symptoms and potential biomarkers.

METHODS

In this prospective study, we enrolled 54 MDD patients and 39 controls. Over the course of weeks 1, 2, and 4 participants underwent evaluations, with electroencephalograms (EEG) recorded at baseline and week 1. Our investigation considered five previously identified syndromal factors derived from the 17-item Hamilton Depression Rating Scale (17-item HAMD) for assessing depression: core, insomnia, somatic anxiety, psychomotor-insight, and anorexia. We assessed treatment response and EEG characteristics across all syndromal factors and total scores, all of which are based on the 17-item HAMD. To analyze the topology of brain networks, we employed functional connectivity (FC) and a graph theory-based method across various frequency bands.

RESULTS

The healthy control group had notably higher values in delta band EEG FC compared to the MDD patient group. Similar distinctions were observed between the responder and non-responder patient groups. Further exploration of baseline FC values across distinct syndromal factors revealed significant variations among the core, psychomotor-insight, and anorexia subgroups when using a specific graph theory-based approach, focusing on global efficiency and average clustering coefficient.

LIMITATIONS

Different antidepressants were included in this study. Therefore, the results should be interpreted with caution.

CONCLUSIONS

Our findings suggest that delta band EEG FC holds promise as a valuable predictor of antidepressant efficacy. It demonstrates an ability to adapt to individual variations in depressive symptomatology, offering insights into personalized treatment for patients with depression.

Resting-state electroencephalogram in drug-free subjects with at-risk mental states who later developed psychosis: a low-resolution electromagnetic tomography analysis

Background and objectives

Several studies have reported on the resting-state electroencephalogram (EEG) power in patients with schizophrenia, with a decrease in α (especially α2) and an increase in δ and β1 power compared with healthy control; however, reports on at-risk mental states (ARMS) are few. In this study, we measured the resting-state EEG power in ARMS, and investigated its features and the relationship between the power of the frequency bands and their diagnostic outcomes.

Methods

Patients with ARMS who were not on any psychotropic medication and met the Comprehensive Assessment of At-Risk Mental State criteria were included. Patients who developed psychotic disorders were labeled as the ARMS-P group, while patients with ARMS who were followed up prospectively for more than 2 years and did not develop psychotic disorders were classified as the ARMS-NP group. EEGs were measured in the resting state, and frequencies were analyzed using standardized low-resolution brain electromagnetic tomography (sLORETA). Seven bands (δ, θ, α1, α2, β1-3) underwent analysis. The sLORETA values (current source density [CSD]) were compared between the ARMS-P and ARMS-NP groups. Clinical symptoms were assessed at the time of EEG measurements using the Positive and Negative Syndrome Scale (PANSS).

Results

Of the 39 patients included (25 males, 14 females, 18.8 ± 4.5 years old), eight developed psychotic disorders (ARMS-P). The ARMS-P group exhibited significantly higher CSD in the β1 power within areas of the left middle frontal gyrus (MFG) compared with the ARMS-NP group (best match: X = -35, Y = 25, Z = 50 [MNI coordinates], Area 8, CSD = 2.33, p < 0.05). There was a significant positive correlation between the β1/α ratio of the CSD at left MFG and the Somatic concern score measured by the PANSS.

Discussion

Increased β1 power was observed in the resting EEG before the onset of psychosis and correlated with a symptom. This suggests that resting EEG power may be a useful marker for predicting future conversion to psychosis and clinical symptoms in patients with ARMS.

Classification of First-Episode Psychosis with EEG Signals: ciSSA and Machine Learning Approach

First-episode psychosis (FEP) typically marks the onset of severe psychiatric disorders and represents a critical period in the field of mental health. The early diagnosis of this condition is essential for timely intervention and improved clinical outcomes. In this study, the classification of FEP was investigated using the analysis of electroencephalography (EEG) signals and circulant spectrum analysis (ciSSA) sub-band signals. FEP poses a significant diagnostic challenge in the realm of mental health, and it is aimed at introducing a novel and effective approach for early diagnosis. To achieve this, the LASSO method was utilized to select the most significant features derived from entropy, frequency, and statistical-based characteristics obtained from ciSSA sub-band signals, as well as their hybrid combinations. Subsequently, a high-performance classification model has been developed using machine learning techniques, including ensemble, support vector machine (SVM), and artificial neural network (ANN) methods. The results of this study demonstrated that the hybrid features extracted from EEG signals' ciSSA sub-bands, in combination with the SVM method, achieved a high level of performance, with an area under curve (AUC) of 0.9893, an accuracy of 96.23%, a sensitivity of 0.966, a specificity of 0.956, a precision of 0.9667, and an F1 score of 0.9666. This has revealed the effectiveness of the ciSSA-based method for classifying FEP from EEG signals.

Forecasting prognostic trajectories with mismatch negativity in early psychosis

BACKGROUND

Prognostic heterogeneity in early psychosis patients yields significant difficulties in determining the degree and duration of early intervention; this heterogeneity highlights the need for prognostic biomarkers. Although mismatch negativity (MMN) has been widely studied across early phases of psychotic disorders, its potential as a common prognostic biomarker in early periods, such as clinical high risk (CHR) for psychosis and first-episode psychosis (FEP), has not been fully studied.

METHODS

A total of 104 FEP patients, 102 CHR individuals, and 107 healthy controls (HCs) participated in baseline MMN recording. Clinical outcomes were assessed; 17 FEP patients were treatment resistant, 73 FEP patients were nonresistant, 56 CHR individuals were nonremitters (15 transitioned to a psychotic disorder), and 22 CHR subjects were remitters. Baseline MMN amplitudes were compared across clinical outcome groups and tested for utility prognostic biomarkers using binary logistic regression.

RESULTS

MMN amplitudes were greatest in HCs, intermediate in CHR subjects, and smallest in FEP patients. In the clinical outcome groups, MMN amplitudes were reduced from the baseline in both FEP and CHR patients with poor prognostic trajectories. Reduced baseline MMN amplitudes were a significant predictor of later treatment resistance in FEP patients [Exp(β) = 2.100, 95% confidence interval (CI) 1.104-3.993, p = 0.024] and nonremission in CHR individuals [Exp(β) = 1.898, 95% CI 1.065-3.374, p = 0.030].

CONCLUSIONS

These findings suggest that MMN could be used as a common prognostic biomarker across early psychosis periods, which will aid clinical decisions for early intervention.

EEG-Based Measures in At-Risk Mental State and Early Stages of Schizophrenia: A Systematic Review

Introduction: Electrophysiological (EEG) abnormalities in subjects with schizophrenia have been largely reported. In the last decades, research has shifted to the identification of electrophysiological alterations in the prodromal and early phases of the disorder, focusing on the prediction of clinical and functional outcome. The identification of neuronal aberrations in subjects with a first episode of psychosis (FEP) and in those at ultra high-risk (UHR) or clinical high-risk (CHR) to develop a psychosis is crucial to implement adequate interventions, reduce the rate of transition to psychosis, as well as the risk of irreversible functioning impairment. The aim of the review is to provide an up-to-date synthesis of the electrophysiological findings in the at-risk mental state and early stages of schizophrenia. Methods: A systematic review of English articles using Pubmed, Scopus, and PsychINFO was undertaken in July 2020. Additional studies were identified by hand-search. Electrophysiological studies that included at least one group of FEP or subjects at risk to develop psychosis, compared to healthy controls (HCs), were considered. The heterogeneity of the studies prevented a quantitative synthesis. Results: Out of 319 records screened, 133 studies were included in a final qualitative synthesis. Included studies were mainly carried out using frequency analysis, microstates and event-related potentials. The most common findings included an increase in delta and gamma power, an impairment in sensory gating assessed through P50 and N100 and a reduction of Mismatch Negativity and P300 amplitude in at-risk mental state and early stages of schizophrenia. Progressive changes in some of these electrophysiological measures were associated with transition to psychosis and disease course. Heterogeneous data have been reported for indices evaluating synchrony, connectivity, and evoked-responses in different frequency bands. Conclusions: Multiple EEG-indices were altered during at-risk mental state and early stages of schizophrenia, supporting the hypothesis that cerebral network dysfunctions appear already before the onset of the disorder. Some of these alterations demonstrated association with transition to psychosis or poor functional outcome. However, heterogeneity in subjects' inclusion criteria, clinical measures and electrophysiological methods prevents drawing solid conclusions. Large prospective studies are needed to consolidate findings concerning electrophysiological markers of clinical and functional outcome.

Evaluation of a Machine Learning Model Based on Pretreatment Symptoms and Electroencephalographic Features to Predict Outcomes of Antidepressant Treatment in Adults With Depression: A Prespecified Secondary Analysis of a Randomized Clinical Trial

IMPORTANCE

Despite the high prevalence and potential outcomes of major depressive disorder, whether and how patients will respond to antidepressant medications is not easily predicted.

OBJECTIVE

To identify the extent to which a machine learning approach, using gradient-boosted decision trees, can predict acute improvement for individual depressive symptoms with antidepressants based on pretreatment symptom scores and electroencephalographic (EEG) measures.

DESIGN, SETTING, AND PARTICIPANTS

This prognostic study analyzed data collected as part of the International Study to Predict Optimized Treatment in Depression, a randomized, prospective open-label trial to identify clinically useful predictors and moderators of response to commonly used first-line antidepressant medications. Data collection was conducted at 20 sites spanning 5 countries and including 518 adult outpatients (18-65 years of age) from primary care or specialty care practices who received a diagnosis of current major depressive disorder between December 1, 2008, and September 30, 2013. Patients were antidepressant medication naive or willing to undergo a 1-week washout period of any nonprotocol antidepressant medication. Statistical analysis was conducted from January 5 to June 30, 2019.

EXPOSURES

Participants with major depressive disorder were randomized in a 1:1:1 ratio to undergo 8 weeks of treatment with escitalopram oxalate (n = 162), sertraline hydrochloride (n = 176), or extended-release venlafaxine hydrochloride (n = 180).

MAIN OUTCOMES AND MEASURES

The primary objective was to predict improvement in individual symptoms, defined as the difference in score for each of the symptoms on the 21-item Hamilton Rating Scale for Depression from baseline to week 8, evaluated using the C index.

RESULTS

The resulting data set contained 518 patients (274 women; mean [SD] age, 39.0 [12.6] years; mean [SD] 21-item Hamilton Rating Scale for Depression score improvement, 13.0 [7.0]). With the use of 5-fold cross-validation for evaluation, the machine learning model achieved C index scores of 0.8 or higher on 12 of 21 clinician-rated symptoms, with the highest C index score of 0.963 (95% CI, 0.939-1.000) for loss of insight. The importance of any single EEG feature was higher than 5% for prediction of 7 symptoms, with the most important EEG features being the absolute delta band power at the occipital electrode sites (O1, 18.8%; Oz, 6.7%) for loss of insight. Over and above the use of baseline symptom scores alone, the use of both EEG and baseline symptom features was associated with a significant increase in the C index for improvement in 4 symptoms: loss of insight (C index increase, 0.012 [95% CI, 0.001-0.020]), energy loss (C index increase, 0.035 [95% CI, 0.011-0.059]), appetite changes (C index increase, 0.017 [95% CI, 0.003-0.030]), and psychomotor retardation (C index increase, 0.020 [95% CI, 0.008-0.032]).

CONCLUSIONS AND RELEVANCE

This study suggests that machine learning may be used to identify independent associations of symptoms and EEG features to predict antidepressant-associated improvements in specific symptoms of depression. The approach should next be prospectively validated in clinical trials and settings.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT00693849.