Predicting individual improvement in schizophrenia symptom severity at 1-year follow-up: Comparison of connectomic, structural, and clinical predictors

Aberrant connectivity in the hippocampus, bilateral insula and temporal poles precedes treatment resistance in first-episode psychosis: a prospective resting-state functional magnetic resonance imaging study with connectivity concordance mapping

Functional connectivity resting-state functional magnetic resonance imaging has been proposed to predict antipsychotic treatment response in schizophrenia. However, only a few prospective studies have examined baseline resting-state functional magnetic resonance imaging data in drug-naïve first-episode schizophrenia patients with regard to subsequent treatment response. Data-driven approaches to conceptualize and measure functional connectivity patterns vary broadly, and model-free, voxel-wise, whole-brain analysis techniques are scarce. Here, we apply such a method, called connectivity concordance mapping to resting-state functional magnetic resonance imaging data acquired from an Asian sample (n = 60) with first-episode psychosis, prior to pharmaceutical treatment. Using a longitudinal design, 12 months after the resting-state functional magnetic resonance imaging, we measured and classified patients into two groups based on psychometric testing: treatment responsive and treatment resistant. Next, we compared the two groups' connectivity concordance maps that were derived from the resting-state functional magnetic resonance imaging data at baseline. We have identified consistently higher functional connectivity in the treatment-resistant group in a network including the left hippocampus, bilateral insula and temporal poles. These data-driven novel findings can help researchers to consider new regions of interest and facilitate biomarker development in order to identify treatment-resistant schizophrenia patients early, in advance of treatment and at the time of their first psychotic episode.

Improved clinical outcome prediction in depression using neurodynamics in an emotional face-matching functional MRI task

Introduction

Approximately one in six people will experience an episode of major depressive disorder (MDD) in their lifetime. Effective treatment is hindered by subjective clinical decision-making and a lack of objective prognostic biomarkers. Functional MRI (fMRI) could provide such an objective measure but the majority of MDD studies has focused on static approaches, disregarding the rapidly changing nature of the brain. In this study, we aim to predict depression severity changes at 3 and 6 months using dynamic fMRI features.

Methods

For our research, we acquired a longitudinal dataset of 32 MDD patients with fMRI scans acquired at baseline and clinical follow-ups 3 and 6 months later. Several measures were derived from an emotion face-matching fMRI dataset: activity in brain regions, static and dynamic functional connectivity between functional brain networks (FBNs) and two measures from a wavelet coherence analysis approach. All fMRI features were evaluated independently, with and without demographic and clinical parameters. Patients were divided into two classes based on changes in depression severity at both follow-ups.

Results

The number of coherence clusters (nCC) between FBNs, reflecting the total number of interactions (either synchronous, anti-synchronous or causal), resulted in the highest predictive performance. The nCC-based classifier achieved 87.5% and 77.4% accuracy for the 3- and 6-months change in severity, respectively. Furthermore, regression analyses supported the potential of nCC for predicting depression severity on a continuous scale. The posterior default mode network (DMN), dorsal attention network (DAN) and two visual networks were the most important networks in the optimal nCC models. Reduced nCC was associated with a poorer depression course, suggesting deficits in sustained attention to and coping with emotion-related faces. An ensemble of classifiers with demographic, clinical and lead coherence features, a measure of dynamic causality, resulted in a 3-months clinical outcome prediction accuracy of 81.2%.

Discussion

The dynamic wavelet features demonstrated high accuracy in predicting individual depression severity change. Features describing brain dynamics could enhance understanding of depression and support clinical decision-making. Further studies are required to evaluate their robustness and replicability in larger cohorts.

fMRI connectivity as a biomarker of antipsychotic treatment response: A systematic review

BACKGROUND

Antipsychotic drugs are the first-choice therapy for psychotic episodes, but antipsychotic treatment response (AP-R) is unpredictable and only becomes clear after weeks of therapy. A biomarker for AP-R is currently unavailable. We reviewed the evidence for the hypothesis that functional magnetic resonance imaging functional connectivity (fMRI-FC) is a predictor of AP-R or could serve as a biomarker for AP-R in psychosis.

METHOD

A systematic review of longitudinal fMRI studies examining the predictive performance and relationship between FC and AP-R was performed following PRISMA guidelines. Technical and clinical aspects were critically assessed for the retrieved studies. We addressed three questions: Q1) is baseline fMRI-FC related to subsequent AP-R; Q2) is AP-R related to a change in fMRI-FC; and Q3) can baseline fMRI-FC predict subsequent AP-R?

RESULTS

In total, 28 articles were included. Most studies were of good quality. fMRI-FC analysis pipelines included seed-based-, independent component- / canonical correlation analysis, network-based statistics, and graph-theoretical approaches. We found high heterogeneity in methodological approaches and results. For Q1 (N = 17) and Q2 (N = 18), the most consistent evidence was found for FC between the striatum and ventral attention network as a potential biomarker of AP-R. For Q3 (N = 9) accuracy's varied form 50 till 93%, and prediction models were based on FC between various brain regions.

CONCLUSION

The current fMRI-FC literature on AP-R is hampered by heterogeneity of methodological approaches. Methodological uniformity and further improvement of the reliability and validity of fMRI connectivity analysis is needed before fMRI-FC analysis can have a place in clinical applications of antipsychotic treatment.

Online Left-Hemispheric In-Phase Frontoparietal Theta tACS Modulates Theta-Band EEG Source-Based Large-Scale Functional Network Connectivity in Patients with Schizophrenia: A Randomized, Double-Blind, Sham-Controlled Clinical Trial

EEG studies indicated that schizophrenia patients had increased resting-state theta-band functional connectivity, which was associated with negative symptoms. We recently published the first study showing that theta (6 Hz) transcranial alternating current stimulation (tACS) over left prefrontal and parietal cortices during a working memory task for accentuating frontoparietal theta-band synchronization (in-phase theta-tACS) reduced negative symptoms in schizophrenia patients. Here, we hypothesized that in-phase theta-tACS can modulate theta-band large-scale networks connectivity in schizophrenia patients. In this randomized, double-blind, sham-controlled trial, patients received twice-daily, 2 mA, 20-min sessions of in-phase theta-tACS for 5 consecutive weekdays (n = 18) or a sham stimulation (n = 18). Resting-state electroencephalography data were collected at baseline, end of stimulation, and at one-week follow-up. Exact low resolution electromagnetic tomography (eLORETA) was used to compute intra-cortical activity. Lagged phase synchronization (LPS) was used to measure whole-brain source-based functional connectivity across 84 cortical regions at theta frequency (5-7 Hz). EEG data from 35 patients were analyzed. We found that in-phase theta-tACS significantly reduced the LPS between the posterior cingulate (PC) and the parahippocampal gyrus (PHG) in the right hemisphere only at the end of stimulation relative to sham (p = 0.0009, corrected). The reduction in right hemispheric PC-PHG LPS was significantly correlated with negative symptom improvement at the end of the stimulation (r = 0.503, p = 0.039). Our findings suggest that in-phase theta-tACS can modulate theta-band large-scale functional connectivity pertaining to negative symptoms. Considering the failure of right hemispheric PC-PHG functional connectivity to predict improvement in negative symptoms at one-week follow-up, future studies should investigate whether it can serve as a surrogate of treatment response to theta-tACS.

Machine Learning and Non-Affective Psychosis: Identification, Differential Diagnosis, and Treatment

PURPOSE OF REVIEW

This review will cover the most relevant findings on the use of machine learning (ML) techniques in the field of non-affective psychosis, by summarizing the studies published in the last three years focusing on illness detection and treatment.

RECENT FINDINGS

Multiple ML tools that include mostly supervised approaches such as support vector machine, gradient boosting, and random forest showed promising results by applying these algorithms to various sources of data: socio-demographic information, EEG, language, digital content, blood biomarkers, neuroimaging, and electronic health records. However, the overall performance, in the binary classification case, varied from 0.49, which is to be considered very low (i.e., noise), to over 0.90. These results are fully justified by different factors, some of which may be attributable to the preprocessing of the data, the wide variety of the data, and the a-priori setting of hyperparameters. One of the main limitations of the field is the lack of stratification of results based on biological sex, given that psychosis presents differently in men and women; hence, the necessity to tailor identification tools and data analytic strategies. Timely identification and appropriate treatment are key factors in reducing the consequences of psychotic disorders. In recent years, the emergence of new analytical tools based on artificial intelligence such as supervised ML approaches showed promises as a potential breakthrough in this field. However, ML applications in everyday practice are still in its infancy.

Frontal lobe fALFF measured from resting-state fMRI as a prognostic biomarker in first-episode psychosis

Clinical response to antipsychotic drug treatment is highly variable, yet prognostic biomarkers are lacking. The goal of the present study was to test whether the fractional amplitude of low-frequency fluctuations (fALFF), as measured from baseline resting-state fMRI data, can serve as a potential biomarker of treatment response to antipsychotics. Patients in the first episode of psychosis (n = 126) were enrolled in two prospective studies employing second-generation antipsychotics (risperidone or aripiprazole). Patients were scanned at the initiation of treatment on a 3T MRI scanner (Study 1, GE Signa HDx, n = 74; Study 2, Siemens Prisma, n = 52). Voxelwise fALFF derived from baseline resting-state fMRI scans served as the primary measure of interest, providing a hypothesis-free (as opposed to region-of-interest) search for regions of the brain that might be predictive of response. At baseline, patients who would later meet strict criteria for clinical response (defined as two consecutive ratings of much or very much improved on the CGI, as well as a rating of ≤3 on psychosis-related items of the BPRS-A) demonstrated significantly greater baseline fALFF in bilateral orbitofrontal cortex compared to non-responders. Thus, spontaneous activity in orbitofrontal cortex may serve as a prognostic biomarker of antipsychotic treatment.

Predicting Treatment Response in Schizophrenia With Magnetic Resonance Imaging and Polygenic Risk Score

Background: Prior studies have separately demonstrated that magnetic resonance imaging (MRI) and schizophrenia polygenic risk score (PRS) are predictive of antipsychotic medication treatment outcomes in schizophrenia. However, it remains unclear whether MRI combined with PRS can provide superior prognostic performance. Besides, the relative importance of these measures in predictions is not investigated.

Methods: We collected 57 patients with schizophrenia, all of which had baseline MRI and genotype data. All these patients received approximately 6 weeks of antipsychotic medication treatment. Psychotic symptom severity was assessed using the Positive and Negative Syndrome Scale (PANSS) at baseline and follow-up. We divided these patients into responders (N = 20) or non-responders (N = 37) based on whether their percentages of PANSS total reduction were above or below 50%. Nine categories of MRI measures and PRSs with 145 different p-value thresholding ranges were calculated. We trained machine learning classifiers with these baseline predictors to identify whether a patient was a responder or non-responder.

Results: The extreme gradient boosting (XGBoost) technique was applied to build binary classifiers. Using a leave-one-out cross-validation scheme, we achieved an accuracy of 86% with all MRI and PRS features. Other metrics were also estimated, including sensitivity (85%), specificity (86%), F1-score (81%), and area under the receiver operating characteristic curve (0.86). We found excluding a single feature category of gray matter volume (GMV), amplitude of low-frequency fluctuation (ALFF), and surface curvature could lead to a maximum accuracy drop of 10.5%. These three categories contributed more than half of the top 10 important features. Besides, removing PRS features caused a modest accuracy drop (8.8%), which was not the least decrease (1.8%) among all feature categories.

Conclusions: Our classifier using both MRI and PRS features was stable and not biased to predicting either responder or non-responder. Combining with MRI measures, PRS could provide certain extra predictive power of antipsychotic medication treatment outcomes in schizophrenia. PRS exhibited medium importance in predictions, lower than GMV, ALFF, and surface curvature, but higher than measures of cortical thickness, cortical volume, and surface sulcal depth. Our findings inform the contributions of PRS in predictions of treatment outcomes in schizophrenia.

Resting-state functional connectivity predictors of treatment response in schizophrenia - A systematic review and meta-analysis

We aimed to systematically synthesize and quantify the utility of pre-treatment resting-state functional magnetic resonance imaging (rs-fMRI) in predicting antipsychotic response in schizophrenia. We searched the PubMed/MEDLINE database for studies that examined the magnitude of association between baseline rs-fMRI assessment and subsequent response to antipsychotic treatment in persons with schizophrenia. We also performed meta-analyses for quantifying the magnitude and accuracy of predicting response defined continuously and categorically. Data from 22 datasets examining 1280 individuals identified striatal and default mode network functional segregation and integration metrics as consistent determinants of treatment response. The pooled correlation coefficient for predicting improvement in total symptoms measured continuously was ~0.47 (12 datasets; 95% CI: 0.35 to 0.59). The pooled odds ratio of predicting categorically defined treatment response was 12.66 (nine datasets; 95% CI: 7.91-20.29), with 81% sensitivity and 76% specificity. rs-fMRI holds promise as a predictive biomarker of antipsychotic treatment response in schizophrenia. Future efforts need to focus on refining feature characterization to improve prediction accuracy, validate prediction models, and evaluate their implementation in clinical practice.

Predicting individual improvement in schizophrenia symptom severity at 1-year follow-up: Comparison of connectomic, structural, and clinical predictors

In a machine learning setting, this study aims to compare the prognostic utility of connectomic, brain structural, and clinical/demographic predictors of individual change in symptom severity in individuals with schizophrenia. Symptom severity at baseline and 1-year follow-up was assessed in 30 individuals with a schizophrenia-spectrum disorder using the Brief Psychiatric Rating Scale. Structural and functional neuroimaging was acquired in all individuals at baseline. Machine learning classifiers were trained to predict whether individuals improved or worsened with respect to positive, negative, and overall symptom severity. Classifiers were trained using various combinations of predictors, including regional cortical thickness and gray matter volume, static and dynamic resting-state connectivity, and/or baseline clinical and demographic variables. Relative change in overall symptom severity between baseline and 1-year follow-up varied markedly among individuals (interquartile range: 55%). Dynamic resting-state connectivity measured within the default-mode network was the most accurate single predictor of change in positive (accuracy: 87%), negative (83%), and overall symptom severity (77%) at follow-up. Incorporating predictors based on regional cortical thickness, gray matter volume, and baseline clinical variables did not markedly improve prediction accuracy and the prognostic utility of these predictors in isolation was moderate (<70%). Worsening negative symptoms at 1-year follow-up were predicted by hyper-connectivity and hypo-dynamism within the default-mode network at baseline assessment, while hypo-connectivity and hyper-dynamism predicted worsening positive symptoms. Given the modest sample size investigated, we recommend giving precedence to the relative ranking of the predictors investigated in this study, rather than the prediction accuracy estimates.