Baseline structural and functional magnetic resonance imaging predicts early treatment response in schizophrenia with radiomics strategy

Radiomic detection of abnormal brain regions in tuberous sclerosis complex

BACKGROUND

Radiomics refers to the extraction of quantitative information from medical images and is most commonly utilized in oncology to provide ancillary information for solid tumor diagnosis, prognosis, and treatment response. The traditional radiomic pipeline involves segmentation of volumes of interest with comparison to normal brain. In other neurologic disorders, such as epilepsy, lesion delineation may be difficult or impossible due to poor anatomic definition, small size, and multifocal or diffuse distribution. Tuberous sclerosis complex (TSC) is a rare genetic disease in which brain magnetic resonance imaging (MRI) demonstrates multifocal abnormalities with variable imaging and epileptogenic features.

PURPOSE

The purpose of this study was to develop a radiomic workflow for identification of abnormal brain regions in TSC, using a whole-brain atlas-based approach with generation of heatmaps based on signal deviation from normal controls.

METHODS

This was a retrospective pilot study utilizing high-resolution whole-brain 3D FLAIR MRI datasets from retrospective enrollment of tuberous sclerosis complex (TSC) patients and normal controls. Subjects underwent MRI including high-resolution 3D FLAIR sequences. Preprocessing included skull stripping, coregistration, and intensity normalization. Using the Brainnetome and Harvard-Oxford atlases, brain regions were parcellated into 318 discrete regions. Expert neuroradiologists spatially labeled all tubers in TSC patients using ITK-SNAP. The pyradiomics toolbox was used to extract 88 radiomic features based on IBSI guidelines, comparing tuber-affected and non-tuber-affected parenchyma in TSC patients, as well as normal brain tissue in control patients. For model training and validation, regions with tubers from 20 TSC patients and 30 normal control subjects were randomly divided into two training sets (80%) and two validation sets (20%). Additional model testing was performed on a separate group of 20 healthy controls. LASSO (least absolute shrinkage and selection operator) was used to perform variable selection and regularization to identify regions containing tubers. Relevant radiomic features selected by LASSO were combined to produce a radiomic score ω, defined as the sum of squared differences from average control group values. Region-specific ω scores were converted to heat maps and spatially coregistered with brain MRI to reflect overall radiomic deviation from normal.

RESULTS

The proposed radiomic workflow allows for quantification of deviation from normal in 318 regions of the brain with the use of a summative radiomic score ω. This score can be used to generate spatially registered heatmaps to identify brain regions with radiomic abnormalities. The pilot study of TSC showed radiomic scores ω that were statistically different in regions containing tubers from regions without tubers/normal brain (p < 0.0001). Our model exhibits an AUC of 0.81 (95% confidence interval: 0.78-0.84) on the testing set, and the best threshold obtained on the training set, when applied to the testing set, allows us to identify regions with tubers with a specificity of 0.91 and a sensitivity of 0.60.

CONCLUSION

We describe a whole-brain atlas-based radiomic approach to identify abnormal brain regions in TSC patients. This approach may be helpful for identifying specific regions of interest based on relatively greater signal deviation, particularly in clinical scenarios with numerous or poorly defined anatomic lesions.

Prediction of Clinical Outcomes in Psychotic Disorders Using Artificial Intelligence Methods: A Scoping Review

BACKGROUND

Psychotic disorders are major psychiatric disorders that can impact multiple domains including physical, social, and psychological functioning within individuals with these conditions. Being able to better predict the outcomes of psychotic disorders will allow clinicians to identify illness subgroups and optimize treatment strategies in a timely manner.

OBJECTIVE

In this scoping review, we aimed to examine the accuracy of the use of artificial intelligence (AI) methods in predicting the clinical outcomes of patients with psychotic disorders as well as determine the relevant predictors of these outcomes.

METHODS

This review was guided by the PRISMA Guidelines for Scoping Reviews. Seven electronic databases were searched for relevant published articles in English until 1 February 2024.

RESULTS

Thirty articles were included in this review. These studies were mainly conducted in the West (63%) and Asia (37%) and published within the last 5 years (83.3%). The clinical outcomes included symptomatic improvements, illness course, and social functioning. The machine learning models utilized data from various sources including clinical, cognitive, and biological variables such as genetic, neuroimaging measures. In terms of main machine learning models used, the most common approaches were support vector machine, random forest, logistic regression, and linear regression models. No specific machine learning approach outperformed the other approaches consistently across the studies, and an overall range of predictive accuracy was observed with an AUC from 0.58 to 0.95. Specific predictors of clinical outcomes included demographic characteristics (gender, socioeconomic status, accommodation, education, and employment); social factors (activity level and interpersonal relationships); illness features (number of relapses, duration of relapses, hospitalization rates, cognitive impairments, and negative and disorganization symptoms); treatment (prescription of first-generation antipsychotics, high antipsychotic doses, clozapine, use of electroconvulsive therapy, and presence of metabolic syndrome); and structural and functional neuroimaging abnormalities, especially involving the temporal and frontal brain regions.

CONCLUSIONS

The current review highlights the potential and need to further refine AI and machine learning models in parsing out the complex interplay of specific variables that contribute to the clinical outcome prediction of psychotic disorders.

Association between degree centrality and neurocognitive impairments in patients with Schizophrenia: A Longitudinal rs-fMRI Study

BACKGROUND

Evidence indicates that patients with schizophrenia (SZ) experience significant changes in their functional connectivity during antipsychotic treatment. Despite previous reports of changes in brain network degree centrality (DC) in patients with schizophrenia, the relationship between brain DC changes and neurocognitive improvement in patients with SZ after antipsychotic treatment remains elusive.

METHODS

A total of 74 patients with acute episodes of chronic SZ and 53 age- and sex-matched healthy controls were recruited. The Positive and Negative Syndrome Scale (PANSS), Symbol Digit Modalities Test, digital span test (DST), and verbal fluency test were used to evaluate the clinical symptoms and cognitive performance of the patients with SZ. Patients with SZ were treated with antipsychotics for six weeks starting at baseline and underwent MRI and clinical interviews at baseline and after six weeks, respectively. We then divided the patients with SZ into responding (RS) and non-responding (NRS) groups based on the PANSS scores (reduction rate of PANSS ≥50%). DC was calculated and analyzed to determine its correlation with clinical symptoms and cognitive performance.

RESULTS

After antipsychotic treatment, the patients with SZ showed significant improvements in clinical symptoms, semantic fluency performance. Correlation analysis revealed that the degree of DC increase in the left anterior inferior parietal lobe (aIPL) after treatment was negatively correlated with changes in the excitement score (r = -0.256, p = 0.048, adjusted p = 0.080), but this correlation failed the multiple test correction. Patients with SZ showed a significant negative correlation between DC values in the left aIPL and DST scores after treatment, which was not observed at the baseline (r = -0.359, p = 0.005, adjusted p = 0.047). In addition, we did not find a significant difference in DC between the RS and NRS groups, neither at baseline nor after treatment.

CONCLUSIONS

The results suggested that DC changes in patients with SZ after antipsychotic treatment are correlated with neurocognitive performance. Our findings provide new insights into the neuropathological mechanisms underlying antipsychotic treatment of SZ.

Multimodal workflows optimally predict response to repetitive transcranial magnetic stimulation in patients with schizophrenia: a multisite machine learning analysis

The response variability to repetitive transcranial magnetic stimulation (rTMS) challenges the effective use of this treatment option in patients with schizophrenia. This variability may be deciphered by leveraging predictive information in structural MRI, clinical, sociodemographic, and genetic data using artificial intelligence. We developed and cross-validated rTMS response prediction models in patients with schizophrenia drawn from the multisite RESIS trial. The models incorporated pre-treatment sMRI, clinical, sociodemographic, and polygenic risk score (PRS) data. Patients were randomly assigned to receive active (N = 45) or sham (N = 47) rTMS treatment. The prediction target was individual response, defined as ≥20% reduction in pre-treatment negative symptom sum scores of the Positive and Negative Syndrome Scale. Our multimodal sequential prediction workflow achieved a balanced accuracy (BAC) of 94% (non-responders: 92%, responders: 95%) in the active-treated group and 50% in the sham-treated group. The clinical, clinical + PRS, and sMRI-based classifiers yielded BACs of 65%, 76%, and 80%, respectively. Apparent sadness, inability to feel, educational attainment PRS, and unemployment were most predictive of non-response in the clinical + PRS model, while grey matter density reductions in the default mode, limbic networks, and the cerebellum were most predictive in the sMRI model. Our sequential modelling approach provided superior predictive performance while minimising the diagnostic burden in the clinical setting. Predictive patterns suggest that rTMS responders may have higher levels of brain grey matter in the default mode and salience networks which increases their likelihood of profiting from plasticity-inducing brain stimulation methods, such as rTMS. The future clinical implementation of our models requires findings to be replicated at the international scale using stratified clinical trial designs.

Large-scale mechanism hypothesis and research prospects of cognitive impairment in schizophrenia based on magnetic resonance imaging

Cognitive impairments in schizophrenia are pivotal clinical issues that need to be solved urgently. However, the mechanism remains unknown. It has been suggested that cognitive impairments in schizophrenia are associated with connectome damage, and are especially relevant to the disrupted hub nodes in the frontal and parietal lobes. Activating the dorsolateral prefrontal cortex (DLPFC) via repetitive transcranial magnetic stimulation (rTMS) could result in improved cognition. Based on several previous magnetic resonance imaging (MRI) studies on schizophrenia, we found that the first-episode patients showed connectome damage, as well as abnormal activation and connectivity of the DLPFC and inferior parietal lobule (IPL). Accordingly, we proposed that DLPFC-IPL pathway destruction might mediate connectome damage of cognitive impairments in schizophrenia. In the meantime, with the help of multimodal MRI and noninvasive neuromodulation tool, we may not only validate the hypothesis, but also find IPL as the potential intervention target for cognitive impairments in schizophrenia.

Abnormalities of Regional Brain Activity in Patients With Schizophrenia: A Longitudinal Resting-State fMRI Study

BACKGROUND

Evidence from functional and structural research suggests that abnormal brain activity plays an important role in the pathophysiology of schizophrenia (SZ). However, limited studies have focused on post-treatment changes, and current conclusions are inconsistent.

STUDY DESIGN

We recruited 104 SZ patients to have resting-state functional magnetic resonance imaging scans at baseline and 8 weeks of treatment with second-generation antipsychotics, along with baseline scanning of 86 healthy controls (HCs) for comparison purposes. Individual regional homogeneity (ReHo), amplitude of low-frequency fluctuations (ALFF), and degree centrality values were calculated to evaluate the functional activity. The Positive and Negative Syndrome Scale (PANSS) and MATRICS Consensus Cognitive Battery were applied to measure psychiatric symptoms and cognitive impairment in SZ patients.

RESULTS

Compared with HCs at baseline, SZ patients had higher ALFF and ReHo values in the bilateral inferior temporal gyrus, inferior frontal gyrus, and lower ALFF and ReHo values in fusiform gyrus and precuneus. Following 8 weeks of treatment, ReHo was increased in right medial region of the superior frontal gyrus (SFGmed) and decreased in the left middle occipital gyrus and the left postcentral gyrus. Meanwhile, ReHo of the right SFGmed was increased after treatment in the response group (the reduction rate of PANSS ≥50%). Enhanced ALFF in the dorsolateral of SFG correlated with improvement in depressive factor score.

CONCLUSIONS

These findings provide novel evidence for the abnormal functional activity hypothesis of SZ, suggesting that abnormality of right SFGmed can be used as a biomarker of treatment response in SZ.

Increased cortical structural covariance correlates with anhedonia in schizophrenia

Anhedonia is a common symptom in schizophrenia and is closely related to poor functional outcomes. Several lines of evidence reveal that the orbitofrontal cortex plays an important role in anhedonia. In the present study, we aimed to investigate abnormalities in structural covariance within the orbitofrontal subregions, and to further study their role in anticipatory and consummatory anhedonia in schizophrenia. T1 images of 35 schizophrenia patients and 45 healthy controls were obtained. The cortical thickness of 68 cerebral regions parcellated by the Desikan-Killiany (DK) atlas was calculated. The structural covariance within the orbitofrontal subregions was calculated in both schizophrenia and healthy control groups. Stepwise linear regression was performed to examine the relationship between structural covariance and anhedonia in schizophrenia patients. Patients with schizophrenia exhibited higher structural covariance between the left and right medial orbitofrontal thickness, the left lateral orbitofrontal thickness and left pars orbitalis thickness compared to healthy controls (p < 0.05, FDR corrected). This results imply that the increased structural covariance in orbitofrontal thickness may be involved in the process of developing anhedonia in schizophrenia. The result indicated that the increased structural covariance between the left and right medial orbitofrontal thickness might be a protective factor for anticipatory pleasure (B' = 0.420, p = 0.012).

Baseline white matter function predicts short-term treatment response in first-episode schizophrenia

BACKGROUND AND PURPOSE

The detection and characterization of functional activities in the gray matter of schizophrenia (SZ) have been widely explored. However, the relationship between resting-state functional signals in the white matter of first-episode SZ and short-term treatment response remains unclear.

METHODS

Thirty-six patients with first-episode SZ and 44 matched healthy controls were recruited in this study. Patients were classified as nonresponders and responders based on response to antipsychotic medication during a single hospitalization. The fractional amplitude of low-frequency fluctuation (fALFF), regional homogeneity (ReHo), and functional connectivity (FC) of white matter were calculated. The relationships between functional changes and clinical features were analyzed. In addition, voxel-based morphometry was performed to analyze the white matter volume.

RESULTS

One-way analysis of variance showed significant differences of fALFF and ReHo in the left posterior thalamic radiation and left cingulum (hippocampus) in the patient group, and the areas were regarded as seeds. The FC was calculated between seeds and other white matter networks. Compared with responders, nonresponders showed significantly increased FC between the left cingulum (hippocampus) and left posterior thalamic radiation, splenium of corpus callosum, and left tapetum, and were associated with the changes of clinical assessment. However, there was no difference in white matter volume between groups.

CONCLUSION

Our work provides a novel insight that psycho-neuroimaging-based white matter function holds promise for influencing the clinical diagnosis and treatment of SZ.

Machine learning methods to predict outcomes of pharmacological treatment in psychosis

In recent years, machine learning (ML) has been a promising approach in the research of treatment outcome prediction in psychosis. In this study, we reviewed ML studies using different neuroimaging, neurophysiological, genetic, and clinical features to predict antipsychotic treatment outcomes in patients at different stages of schizophrenia. Literature available on PubMed until March 2022 was reviewed. Overall, 28 studies were included, among them 23 using a single-modality approach and 5 combining data from multiple modalities. The majority of included studies considered structural and functional neuroimaging biomarkers as predictive features used in ML models. Specifically, functional magnetic resonance imaging (fMRI) features contributed to antipsychotic treatment response prediction of psychosis with good accuracies. Additionally, several studies found that ML models based on clinical features might present adequate predictive ability. Importantly, by examining the additive effects of combining features, the predictive value might be improved by applying multimodal ML approaches. However, most of the included studies presented several limitations, such as small sample sizes and a lack of replication tests. Moreover, considerable clinical and analytical heterogeneity among included studies posed a challenge in synthesizing findings and generating robust overall conclusions. Despite the complexity and heterogeneity of methodology, prognostic features, clinical presentation, and treatment approaches, studies included in this review suggest that ML tools may have the potential to predict treatment outcomes of psychosis accurately. Future studies need to focus on refining feature characterization, validating prediction models, and evaluate their translation in real-world clinical practice.

Introduction to radiomics for a clinical audience

Radiomics is a rapidly developing field of research focused on the extraction of quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding of disease processes and provide clinical decision support. To date, most radiomics research has been focused on oncological applications; however, it is increasingly being used in a raft of other diseases. This review gives an overview of radiomics for a clinical audience, including the radiomics pipeline and the common pitfalls associated with each stage. Key studies in oncology are presented with a focus on both those that use radiomics analysis alone and those that integrate its use with other multimodal data streams. Importantly, clinical applications outside oncology are also presented. Finally, we conclude by offering a vision for radiomics research in the future, including how it might impact our practice as radiologists.

Incidence and factors associated of early non-response in first-treatment and drug-naïve patients with schizophrenia: a real-world study

Background

Schizophrenia is a severe and persistent mental condition that causes disability. For subsequent clinical care, it is extremely practical to effectively differentiate between patients who respond to therapy quickly and those who do not. This study set out to document the prevalence and risk factors for patient early non-response.

Methods

The current study included 143 individuals with first-treatment and drug-naïve (FTDN) schizophrenia. Patients were classified as early non-responders based on a Positive and Negative Symptom Scale (PANSS) score reduction of less than 20% after 2 weeks of treatment, otherwise as early responders. Clinical subgroups' differences in demographic data and general clinical data were compared, and variables related to early non-response to therapy were examined.

Results

Two weeks later, a total of 73 patients were described as early non-responders, with an incidence of 51.05%. The early non-response subgroup had significantly higher PANSS scores, Positive symptom subscale (PSS) scores, General psychopathology subscale (GPS) scores, Clinical global impression scale - severity of illness (CGI-SI) and Fasting blood glucose (FBG) levels compared to the early-response subgroup. CGI-SI and FBG were risk factors for early non-response.

Conclusion

High rates of early non-response have been seen in FTDN schizophrenia patients, and risk variables for predicting early non-response include CGI-SI scores and FBG levels. However, we need more in-depth studies to confirm the generalizable range of these two parameters.

Radiomic features of gray matter in never-treated first-episode schizophrenia

Alterations of radiomic features (RFs) in gray matter are observed in schizophrenia, of which the results may be limited by small study samples and confounding effects of drug therapies. We tested for RFs alterations of gray matter in never-treated first-episode schizophrenia (NT-FES) patients and examined their associations with known gene expression profiles. RFs were examined in the first sample with 197 NT-FES and 178 healthy controls (HCs) and validated in the second independent sample (90 NT-FES and 74 HCs). One-year follow-up data were available from 87 patients to determine whether RFs were associated with treatment outcomes. Associations between identified RFs in NT-FES and gene expression profiles were evaluated. NT-FES exhibited alterations of 30 RFs, with the greatest involvement of microstructural heterogeneity followed by measures of brain region shape. The identified RFs were mainly located in the central executive network, frontal-temporal network, and limbic system. Two baseline RFs with the involvement of microstructural heterogeneity predicted treatment response with moderate accuracy (78% for the first sample, 70% for the second sample). Exploratory analyses indicated that RF alterations were spatially related to the expression of schizophrenia risk genes. In summary, the present findings link brain abnormalities in schizophrenia with molecular features and treatment response.

Graph-Theory-Based Degree Centrality Combined with Machine Learning Algorithms Can Predict Response to Treatment with Antipsychotic Medications in Patients with First-Episode Schizophrenia

Objectives

Schizophrenia (SCZ) is associated with disrupted functional brain connectivity, and antipsychotic medications are the primary and most commonly used treatment for schizophrenia. However, not all patients respond to antipsychotic medications.

Methods

The study is aimed at investigating whether the graph-theory-based degree centrality (DC), derived from resting-state functional MRI (rs-fMRI), can predict the treatment outcomes. rs-fMRI data from 38 SCZ patients were collected and compared with findings from 38 age- and gender-matched healthy controls (HCs). The patients were treated with antipsychotic medications for 16 weeks before undergoing a second rs-fMRI scan. DC data were processed using DPABI and SPM12 software.

Results

SCZ patients at baseline showed increased DC in the frontal and temporal gyrus, anterior cingulate cortex, and precuneus and reduced DC in bilateral subcortical gray matter structures. However, those abnormalities showed a clear renormalization after antipsychotic medication treatments. Support vector machine analysis using leave-one-out cross-validation achieved a correct classification rate of 84.2% (sensitivity 78.9%, specificity 89.5%, and area under the receiver operating characteristic curve (AUC) 0.925) for differentiating effective subjects from ineffective subjects. Brain areas that contributed most to the classification model were mainly located within the bilateral putamen, left inferior frontal gyrus, left middle occipital cortex, bilateral middle frontal gyrus, left cerebellum, left medial frontal gyrus, left inferior temporal gyrus, and left angular. Furthermore, the DC change within the bilateral putamen is negatively correlated with the symptom improvements after treatment.

Conclusions

Our study confirmed that graph-theory-based measures, combined with machine-learning algorithms, can provide crucial insights into pathophysiological mechanisms and the effectiveness of antipsychotic medications.

Diagnosis of Neural Activity among Abnormal Brain Regions in Patients with Major Depressive Disorder by Magnetic Resonance Imaging Features

In order to explore the diagnostic value of magnetic resonance imaging (MRI) for neural activity among abnormal brain regions in patients with major depressive disorder (MDD), thirty patients with MDD (observation group) were selected for comparison with 30 healthy people without MDD (control group). The included subjects were examined by MRI to compare the MRI features and were analyzed for regional homogeneity (ReHo) and amplitude low-frequency fluctuations (ALFF). The results showed that compared with the control group, the brain regions with increased ReHo and ALFF in the observation group were medial frontal gyrus (right), middle temporal lobe (left), inferior parietal lobe (left), and posterior cerebellar lobe (right); the brain region with increased ReHo and ALFF in the observation group was the middle temporal gyrus (right). Compared with the control group, there were significant differences in ReHo and ALFF in the observation group. It was found that the brain function of patients with MDD was abnormal compared with that of the normal subjects, and the brain network activity was also abnormal. MRI features can be used to explore abnormal brain regions in patients with MDD and have positive guiding value.

Mathematical Abilities in School-Aged Children: A Structural Magnetic Resonance Imaging Analysis With Radiomics

Structural magnetic resonance imaging (sMRI) studies have shown that children that differ in some mathematical abilities show differences in gray matter volume mainly in parietal and frontal regions that are involved in number processing, attentional control, and memory. In the present study, a structural neuroimaging analysis based on radiomics and machine learning models is presented with the aim of identifying the brain areas that better predict children’s performance in a variety of mathematical tests. A sample of 77 school-aged children from third to sixth grade were administered four mathematical tests: Math fluency, Calculation, Applied problems and Quantitative concepts as well as a structural brain imaging scan. By extracting radiomics related to the shape, intensity, and texture of specific brain areas, we observed that areas from the frontal, parietal, temporal, and occipital lobes, basal ganglia, and limbic system, were differentially related to children’s performance in the mathematical tests. sMRI-based analyses in the context of mathematical performance have been mainly focused on volumetric measures. However, the results for radiomics-based analysis showed that for these areas, texture features were the most important for the regression models, while volume accounted for less than 15% of the shape importance. These findings highlight the potential of radiomics for more in-depth analysis of medical images for the identification of brain areas related to mathematical abilities.

The Association Between Lentiform Nucleus Function and Cognitive Impairments in Schizophrenia

Introduction: Cognitive decline is the core schizophrenia symptom, which is now well accepted. Holding a role in various aspects of cognition, lentiform nucleus (putamen and globus pallidus) dysfunction contributes to the psychopathology of this disease. However, the effects of lentiform nucleus function on cognitive impairments in schizophrenia are yet to be investigated.

Objectives: We aim to detect the fractional amplitude of low-frequency fluctuation (fALFF) alterations in patients with schizophrenia, and examine how their behavior correlates in relation to the cognitive impairments of the patients.

Methods: All participants underwent magnetic resonance imaging (MRI) and cognitive assessment (digit span and digit symbol coding tests). Screening of brain regions with significant changes in fALFF values was based on analysis of the whole brain. The data were analyzed between Jun 2020 and Mar 2021. There were no interventions beyond the routine therapy determined by their clinicians on the basis of standard clinical practice.

Results: There were 136 patients (75 men and 61 women, 24.1 ± 7.4 years old) and 146 healthy controls (82 men and 64 women, 24.2 ± 5.2 years old) involved in the experiments seriatim. Patients with schizophrenia exhibited decreased raw scores in cognitive tests (p < 0.001) and increased fALFF in the bilateral lentiform nuclei (left: 67 voxels; x = −24, y = −6, z = 3; peak t-value = 6.90; right: 16 voxels; x = 18, y = 0, z = 3; peak t-value = 6.36). The fALFF values in the bilateral lentiform nuclei were positively correlated with digit span-backward test scores (left: r = 0.193, p = 0.027; right: r = 0.190, p = 0.030), and the right lentiform nucleus was positively correlated with digit symbol coding scores (r = 0.209, p = 0.016).

Conclusion: This study demonstrates that cognitive impairments in schizophrenia are associated with lentiform nucleus function as revealed by MRI, involving working memory and processing speed.

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.

Psychiatry in the Digital Age: A Blessing or a Curse?

Social distancing and the shortage of healthcare professionals during the COVID-19 pandemic, the impact of population aging on the healthcare system, as well as the rapid pace of digital innovation are catalyzing the development and implementation of new technologies and digital services in psychiatry. Is this transformation a blessing or a curse for psychiatry? To answer this question, we conducted a literature review covering a broad range of new technologies and eHealth services, including telepsychiatry; computer-, internet-, and app-based cognitive behavioral therapy; virtual reality; digital applied games; a digital medicine system; omics; neuroimaging; machine learning; precision psychiatry; clinical decision support; electronic health records; physician charting; digital language translators; and online mental health resources for patients. We found that eHealth services provide effective, scalable, and cost-efficient options for the treatment of people with limited or no access to mental health care. This review highlights innovative technologies spearheading the way to more effective and safer treatments. We identified artificially intelligent tools that relieve physicians from routine tasks, allowing them to focus on collaborative doctor-patient relationships. The transformation of traditional clinics into digital ones is outlined, and the challenges associated with the successful deployment of digitalization in psychiatry are highlighted.

Thalamus Radiomics-Based Disease Identification and Prediction of Early Treatment Response for Schizophrenia

Background

Emerging evidence suggests structural and functional disruptions of the thalamus in schizophrenia, but whether thalamus abnormalities are able to be used for disease identification and prediction of early treatment response in schizophrenia remains to be determined. This study aims at developing and validating a method of disease identification and prediction of treatment response by multi-dimensional thalamic features derived from magnetic resonance imaging in schizophrenia patients using radiomics approaches.

Methods

A total of 390 subjects, including patients with schizophrenia and healthy controls, participated in this study, among which 109 out of 191 patients had clinical characteristics of early outcome (61 responders and 48 non-responders). Thalamus-based radiomics features were extracted and selected. The diagnostic and predictive capacity of multi-dimensional thalamic features was evaluated using radiomics approach.

Results

Using radiomics features, the classifier accurately discriminated patients from healthy controls, with an accuracy of 68%. The features were further confirmed in prediction and random forest of treatment response, with an accuracy of 75%.

Conclusion

Our study demonstrates a radiomics approach by multiple thalamic features to identify schizophrenia and predict early treatment response. Thalamus-based classification could be promising to apply in schizophrenia definition and treatment selection.