Towards a brain-based predictome of mental illness

A generalizable functional connectivity signature characterizes brain dysfunction and links to rTMS treatment response in cocaine use disorder

Cocaine use disorder (CUD) is a prevalent substance abuse disorder, and repetitive transcranial magnetic stimulation (rTMS) has shown potential in reducing cocaine cravings. However, a robust and replicable biomarker for CUD phenotyping is lacking, and the association between CUD brain phenotypes and treatment response remains unclear. Our study successfully established a cross-validated functional connectivity signature for accurate CUD phenotyping, using resting-state functional magnetic resonance imaging from a discovery cohort, and demonstrated its generalizability in an independent replication cohort. We identified phenotyping FCs involving increased connectivity between the visual network and dorsal attention network, and between the frontoparietal control network and ventral attention network, as well as decreased connectivity between the default mode network and limbic network in CUD patients compared to healthy controls. These abnormal connections correlated significantly with other drug use history and cognitive dysfunctions, e.g., non-planning impulsivity. We further confirmed the prognostic potential of the identified discriminative FCs for rTMS treatment response in CUD patients and found that the treatment-predictive FCs mainly involved the frontoparietal control and default mode networks. Our findings provide new insights into the neurobiological mechanisms of CUD and the association between CUD phenotypes and rTMS treatment response, offering promising targets for future therapeutic development.

Dysconnection and cognition in schizophrenia: A spectral dynamic causal modeling study

Schizophrenia (SZ) is a severe mental disorder characterized by failure of functional integration (aka dysconnection) across the brain. Recent functional connectivity (FC) studies have adopted functional parcellations to define subnetworks of large-scale networks, and to characterize the (dys)connection between them, in normal and clinical populations. While FC examines statistical dependencies between observations, model-based effective connectivity (EC) can disclose the causal influences that underwrite the observed dependencies. In this study, we investigated resting state EC within seven large-scale networks, in 66 SZ and 74 healthy subjects from a public dataset. The results showed that a remarkable 33% of the effective connections (among subnetworks) of the cognitive control network had been pathologically modulated in SZ. Further dysconnection was identified within the visual, default mode and sensorimotor networks of SZ subjects, with 24%, 20%, and 11% aberrant couplings. Overall, the proportion of discriminative connections was remarkably larger in EC (24%) than FC (1%) analysis. Subsequently, to study the neural correlates of impaired cognition in SZ, we conducted a canonical correlation analysis between the EC parameters and the cognitive scores of the patients. As such, the self-inhibitions of supplementary motor area and paracentral lobule (in the sensorimotor network) and the excitatory connection from parahippocampal gyrus to inferior temporal gyrus (in the cognitive control network) were significantly correlated with the social cognition, reasoning/problem solving and working memory capabilities of the patients. Future research can investigate the potential of whole-brain EC as a biomarker for diagnosis of brain disorders and for neuroimaging-based cognitive assessment.

Discriminating Paradoxical and Psychophysiological Insomnia Based on Structural and Functional Brain Images: A Preliminary Machine Learning Study

Insomnia disorder (ID) is a prevalent mental illness. Several behavioral and neuroimaging studies suggested that ID is a heterogenous condition with various subtypes. However, neurobiological alterations in different subtypes of ID are poorly understood. We aimed to assess whether unimodal and multimodal whole-brain neuroimaging measurements can discriminate two commonly described ID subtypes (i.e., paradoxical and psychophysiological insomnia) from each other and healthy subjects. We obtained T1-weighted images and resting-state fMRI from 34 patients with ID and 48 healthy controls. The outcome measures were grey matter volume, cortical thickness, amplitude of low-frequency fluctuation, degree centrality, and regional homogeneity. Subsequently, we applied support vector machines to classify subjects via unimodal and multimodal measures. The results of the multimodal classification were superior to those of unimodal approaches, i.e., we achieved 81% accuracy in separating psychophysiological vs. control, 87% for paradoxical vs. control, and 89% for paradoxical vs. psychophysiological insomnia. This preliminary study provides evidence that structural and functional brain data can help to distinguish two common subtypes of ID from each other and healthy subjects. These initial findings may stimulate further research to identify the underlying mechanism of each subtype and develop personalized treatments for ID in the future.

Prediction of preoperative in-hospital mortality rate in patients with acute aortic dissection by machine learning: a two-centre, retrospective cohort study

OBJECTIVES

To conduct a comprehensive analysis of demographic information, medical history, and blood pressure (BP) and heart rate (HR) variability during hospitalisation so as to establish a predictive model for preoperative in-hospital mortality of patients with acute aortic dissection (AD) by using machine learning techniques.

DESIGN

Retrospective cohort study.

SETTING

Data were collected from the electronic records and the databases of Shanghai Ninth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine and the First Affiliated Hospital of Anhui Medical University between 2004 and 2018.

PARTICIPANTS

380 inpatients diagnosed with acute AD were included in the study.

PRIMARY OUTCOME

Preoperative in-hospital mortality rate.

RESULTS

A total of 55 patients (14.47%) died in the hospital before surgery. The results of the areas under the receiver operating characteristic curves, decision curve analysis and calibration curves indicated that the eXtreme Gradient Boosting (XGBoost) model had the highest accuracy and robustness. According to the SHapley Additive exPlanations analysis of the XGBoost model, Stanford type A, maximum aortic diameter >5.5 cm, high variability in HR, high variability in diastolic BP and involvement of the aortic arch had the greatest impact on the occurrence of in-hospital deaths before surgery. Moreover, the predictive model can accurately predict the preoperative in-hospital mortality rate at the individual level.

CONCLUSION

In the current study, we successfully constructed machine learning models to predict the preoperative in-hospital mortality of patients with acute AD, which can help identify high-risk patients and optimise the clinical decision-making. Further applications in clinical practice require the validation of these models using a large-sample, prospective database.

TRIAL REGISTRATION NUMBER

ChiCTR1900025818.

An Interpretable and Predictive Connectivity-Based Neural Signature for Chronic Cannabis Use

BACKGROUND

Cannabis is one of the most widely used substances in the world, with usage trending upward in recent years. However, although the psychiatric burden associated with maladaptive cannabis use has been well established, reliable and interpretable biomarkers associated with chronic use remain elusive. In this study, we combine large-scale functional magnetic resonance imaging with machine learning and network analysis and develop an interpretable decoding model that offers both accurate prediction and novel insights into chronic cannabis use.

METHODS

Chronic cannabis users (n = 166) and nonusing healthy control subjects (n = 124) completed a cue-elicited craving task during functional magnetic resonance imaging. Linear machine learning methods were used to classify individuals into chronic users and nonusers based on whole-brain functional connectivity. Network analysis was used to identify the most predictive regions and communities.

RESULTS

We obtained high (∼80% out-of-sample) accuracy across 4 different classification models, demonstrating that task-evoked connectivity can successfully differentiate chronic cannabis users from nonusers. We also identified key predictive regions implicating motor, sensory, attention, and craving-related areas, as well as a core set of brain networks that contributed to successful classification. The most predictive networks also strongly correlated with cannabis craving within the chronic user group.

CONCLUSIONS

This novel approach produced a neural signature of chronic cannabis use that is both accurate in terms of out-of-sample prediction and interpretable in terms of predictive networks and their relation to cannabis craving.

A systematic review on the potential use of machine learning to classify major depressive disorder from healthy controls using resting state fMRI measures

BACKGROUND

Major Depressive Disorder (MDD) is a psychiatric disorder characterized by functional brain deficits, as documented by resting-state functional magnetic resonance imaging (rs-fMRI) studies.

AIMS

In recent years, some studies used machine learning (ML) approaches, based on rs-fMRI features, for classifying MDD from healthy controls (HC). In this context, this review aims to provide a comprehensive overview of the results of these studies.

DESIGN

The studies research was performed on 3 online databases, examining English-written articles published before August 5, 2022, that performed a two-class ML classification using rs-fMRI features. The search resulted in 20 eligible studies.

RESULTS

The reviewed studies showed good performance metrics, with better performance achieved when the dataset was restricted to a more homogeneous group in terms of disease severity. Regions within the default mode network, salience network, and central executive network were reported as the most important features in the classification algorithms.

LIMITATIONS

The small sample size together with the methodological and clinical heterogeneity limited the generalizability of the findings.

CONCLUSIONS

In conclusion, ML applied to rs-fMRI features can be a valid approach to classify MDD and HC subjects and to discover features that can be used for additional investigation of the pathophysiology of the disease.

Leveraging Machine Learning for Gaining Neurobiological and Nosological Insights in Psychiatric Research

Much attention is currently devoted to developing diagnostic classifiers for mental disorders. Complementing these efforts, we highlight the potential of machine learning to gain biological insights into the psychopathology and nosology of mental disorders. Studies to this end have mainly used brain imaging data, which can be obtained noninvasively from large cohorts and have repeatedly been argued to reveal potentially intermediate phenotypes. This may become particularly relevant in light of recent efforts to identify magnetic resonance imaging-derived biomarkers that yield insight into pathophysiological processes as well as to refine the taxonomy of mental illness. In particular, the accuracy of machine learning models may be used as dependent variables to identify features relevant to pathophysiology. Moreover, such approaches may help disentangle the dimensional (within diagnosis) and often overlapping (across diagnoses) symptomatology of psychiatric illness. We also point out a multiview perspective that combines data from different sources, bridging molecular and system-level information. Finally, we summarize recent efforts toward a data-driven definition of subtypes or disease entities through unsupervised and semisupervised approaches. The latter, blending unsupervised and supervised concepts, may represent a particularly promising avenue toward dissecting heterogeneous categories. Finally, we raise several technical and conceptual aspects related to the reviewed approaches. In particular, we discuss common pitfalls pertaining to flawed input data or analytic procedures that would likely lead to unreliable outputs.

Topological disruption of high-order functional networks in cognitively preserved Parkinson's disease

AIMS

This study aimed to characterize the topological alterations and classification performance of high-order functional connectivity (HOFC) networks in cognitively preserved patients with Parkinson's disease (PD), relative to low-order FC (LOFC) networks.

METHODS

The topological metrics of the constructed networks (LOFC and HOFC) obtained from fifty-one cognitively normal patients with PD and 60 matched healthy control subjects were analyzed. The discriminative abilities were evaluated using machine learning approach.

RESULTS

The HOFC networks in the PD group showed decreased segregation and integration. The normalized clustering coefficient and small-worldness in the HOFC networks were correlated to motor performance. The altered nodal centralities (distributed in the precuneus, putamen, lingual gyrus, supramarginal gyrus, motor area, postcentral gyrus and inferior occipital gyrus) and intermodular FC (frontoparietal and visual networks, sensorimotor and subcortical networks) were specific to HOFC networks. Several highly connected nodes (thalamus, paracentral lobule, calcarine fissure and precuneus) and improved classification performance were found based on HOFC profiles.

CONCLUSION

This study identified disrupted topology of functional interactions at a high level with extensive alterations in topological properties and improved differentiation ability in patients with PD prior to clinical symptoms of cognitive impairment, providing complementary insights into complex neurodegeneration in PD.

Neuroimaging biomarkers for detecting schizophrenia: A resting-state functional MRI-based radiomics analysis

Schizophrenia (SZ) is a common psychiatric disorder that is difficult to accurately diagnose in clinical practice. Quantifiable biomarkers are urgently required to explore the potential physiological mechanism of SZ and improve its diagnostic accuracy. Thus, this study aimed to identify biomarkers that classify SZ patients and healthy control subjects and investigate the potential neural mechanisms of SZ using degree centrality (DC)- and voxel-mirrored homotopic connectivity (VMHC)-based radiomics. Radiomics features were extracted from DC and VMHC metrics generated via resting-state functional magnetic resonance imaging, and significant features were selected and dimensionality was reduced using t-tests and least absolute shrinkage and selection operator. Subsequently, we built our model using a support vector machine classifier. We observed that our method obtained great classification performance (area under the curve, 0.808; accuracy, 74.02%), and it could be generalized to different brain atlases. The regions that we identified as discriminative features mainly included bilateral dorsal caudate and front-parietal, somatomotor, limbic, and default mode networks. Our findings showed that the radiomics-based machine learning method could facilitate us to understand the potential pathological mechanism of SZ more comprehensively and contribute to the accurate diagnosis of patients with SZ.

Can this data be saved? Techniques for high motion in resting state scans of first grade children

Motion remains a significant technical hurdle in fMRI studies of young children. Our aim was to develop a straightforward and effective method for obtaining and preprocessing resting state data from a high-motion pediatric cohort. This approach combines real-time monitoring of head motion with a preprocessing pipeline that uses volume censoring and concatenation alongside independent component analysis based denoising. We evaluated this method using a sample of 108 first grade children (age 6-8) enrolled in a longitudinal study of math development. Data quality was assessed by analyzing the correlation between participant head motion and two key metrics for resting state data, temporal signal-to-noise and functional connectivity. These correlations should be minimal in the absence of noise-related artifacts. We compared these data quality indicators using several censoring thresholds to determine the necessary degree of censoring. Volume censoring was highly effective at removing motion-corrupted volumes and ICA denoising removed much of the remaining motion artifact. With the censoring threshold set to exclude volumes that exceeded a framewise displacement of 0.3 mm, preprocessed data met rigorous standards for data quality while retaining a large majority of subjects (83 % of participants). Overall, results show it is possible to obtain usable resting-state data despite extreme motion in a group of young, untrained subjects.

Brain morphology predictors of alcohol, tobacco, and cannabis use in adolescence: A systematic review

In the last decade, extensive research has emerged on the predictive value of brain morphology for substance use initiation and related problems during adolescence. This systematic review provides an overview of longitudinal studies on pre-existing brain variations and later initiation of alcohol, tobacco, and cannabis use (N = 18). Adolescent structural neuroimaging studies that started before substance use initiation suggest that a smaller anterior cingulate cortex (ACC) volume, thicker or smaller superior frontal gyrus, and larger nucleus accumbens (NAcc) volume are associated with future alcohol use. Also, both smaller and larger orbitofrontal cortex (OFC) volumes were associated with future cannabis and combined alcohol/cannabis use. Smaller amygdala volumes were related to future daily tobacco smoking. These findings could point to specific vulnerabilities for adolescent substance use, as these brain areas are involved in cognitive control (ACC), reward (NAcc), motivation (OFC), and emotional memory (amygdala). However, the reported findings were inconsistent in directionality and laterality, and the largest study on alcohol use predictors reported null findings. Therefore, large population-based longitudinal studies should investigate the robustness and mechanisms of these associations. We suggested future research directions regarding sample selection, timing of baseline and follow-up measurements, and a harmonization approach of study methods.

Resting-state EEG functional connectivity predicts post-traumatic stress disorder subtypes in veterans

Objective. Post-traumatic stress disorder (PTSD) is highly heterogeneous, and identification of quantifiable biomarkers that could pave the way for targeted treatment remains a challenge. Most previous electroencephalography (EEG) studies on PTSD have been limited to specific handpicked features, and their findings have been highly variable and inconsistent. Therefore, to disentangle the role of promising EEG biomarkers, we developed a machine learning framework to investigate a wide range of commonly used EEG biomarkers in order to identify which features or combinations of features are capable of characterizing PTSD and potential subtypes.Approach. We recorded 5 min of eyes-closed and 5 min of eyes-open resting-state EEG from 202 combat-exposed veterans (53% with probable PTSD and 47% combat-exposed controls). Multiple spectral, temporal, and connectivity features were computed and logistic regression, random forest, and support vector machines with feature selection methods were employed to classify PTSD. To obtain robust results, we performed repeated two-layer cross-validation to test on an entirely unseen test set.Main results. Our classifiers obtained a balanced test accuracy of up to 62.9% for predicting PTSD patients. In addition, we identified two subtypes within PTSD: one where EEG patterns were similar to those of the combat-exposed controls, and another that were characterized by increased global functional connectivity. Our classifier obtained a balanced test accuracy of 79.4% when classifying this PTSD subtype from controls, a clear improvement compared to predicting the whole PTSD group. Interestingly, alpha connectivity in the dorsal and ventral attention network was particularly important for the prediction, and these connections were positively correlated with arousal symptom scores, a central symptom cluster of PTSD.Significance. Taken together, the novel framework presented here demonstrates how unsupervised subtyping can delineate heterogeneity and improve machine learning prediction of PTSD, and may pave the way for better identification of quantifiable biomarkers.

Intellectually able adults with autism spectrum disorder show typical resting-state EEG activity

There is broad interest in discovering quantifiable physiological biomarkers for psychiatric disorders to aid diagnostic assessment. However, finding biomarkers for autism spectrum disorder (ASD) has proven particularly difficult, partly due to high heterogeneity. Here, we recorded five minutes eyes-closed rest electroencephalography (EEG) from 186 adults (51% with ASD and 49% without ASD) and investigated the potential of EEG biomarkers to classify ASD using three conventional machine learning models with two-layer cross-validation. Comprehensive characterization of spectral, temporal and spatial dimensions of source-modelled EEG resulted in 3443 biomarkers per recording. We found no significant group-mean or group-variance differences for any of the EEG features. Interestingly, we obtained validation accuracies above 80%; however, the best machine learning model merely distinguished ASD from the non-autistic comparison group with a mean balanced test accuracy of 56% on the entirely unseen test set. The large drop in model performance between validation and testing, stress the importance of rigorous model evaluation, and further highlights the high heterogeneity in ASD. Overall, the lack of significant differences and weak classification indicates that, at the group level, intellectually able adults with ASD show remarkably typical resting-state EEG.

Multi-modal intermediate integrative methods in neuropsychiatric disorders: A review

The etiology of neuropsychiatric disorders involves complex biological processes at different omics layers, such as genomics, transcriptomics, epigenetics, proteomics, and metabolomics. The advent of high-throughput technology, as well as the availability of large open-source datasets, has ushered in a new era in system biology, necessitating the integration of various types of omics data. The complexity of biological mechanisms, the limitations of integrative strategies, and the heterogeneity of multi-omics data have all presented significant challenges to computational scientists. In comparison to early and late integration, intermediate integration may transform each data type into appropriate intermediate representations using various data transformation techniques, allowing it to capture more complementary information contained in each omics and highlight new interactions across omics layers. Here, we reviewed multi-modal intermediate integrative techniques based on component analysis, matrix factorization, similarity network, multiple kernel learning, Bayesian network, artificial neural networks, and graph transformation, as well as their applications in neuropsychiatric domains. We depicted advancements in these approaches and compared the strengths and weaknesses of each method examined. We believe that our findings will aid researchers in their understanding of the transformation and integration of multi-omics data in neuropsychiatric disorders.

Altered neural flexibility in children with attention-deficit/hyperactivity disorder

Attention-deficit/hyperactivity disorder (ADHD) is one of the most common neurodevelopmental disorders of childhood, and is often characterized by altered executive functioning. Executive function has been found to be supported by flexibility in dynamic brain reconfiguration. Thus, we applied multilayer community detection to resting-state fMRI data in 180 children with ADHD and 180 typically developing children (TDC) to identify alterations in dynamic brain reconfiguration in children with ADHD. We specifically evaluated MR derived neural flexibility, which is thought to underlie cognitive flexibility, or the ability to selectively switch between mental processes. Significantly decreased neural flexibility was observed in the ADHD group at both the whole brain (raw p = 0.0005) and sub-network levels (p < 0.05, FDR corrected), particularly for the default mode network, attention-related networks, executive function-related networks, and primary networks. Furthermore, the subjects with ADHD who received medication exhibited significantly increased neural flexibility (p = 0.025, FDR corrected) when compared to subjects with ADHD who were medication naïve, and their neural flexibility was not statistically different from the TDC group (p = 0.74, FDR corrected). Finally, regional neural flexibility was capable of differentiating ADHD from TDC (Accuracy: 77% for tenfold cross-validation, 74.46% for independent test) and of predicting ADHD severity using clinical measures of symptom severity (R2: 0.2794 for tenfold cross-validation, 0.156 for independent test). In conclusion, the present study found that neural flexibility is altered in children with ADHD and demonstrated the potential clinical utility of neural flexibility to identify children with ADHD, as well as to monitor treatment responses and disease severity.

A novel neighborhood rough set-based feature selection method and its application to biomarker identification of schizophrenia

Feature selection can disclose biomarkers of mental disorders that have unclear biological mechanisms. Although neighborhood rough set (NRS) has been applied to discover important sparse features, it has hardly ever been utilized in neuroimaging-based biomarker identification, probably due to the inadequate feature evaluation metric and incomplete information provided under a single-granularity. Here, we propose a new NRS-based feature selection method and successfully identify brain functional connectivity biomarkers of schizophrenia (SZ) using functional magnetic resonance imaging (fMRI) data. Specifically, we develop a new weighted metric based on NRS combined with information entropy to evaluate the capacity of features in distinguishing different groups. Inspired by multi-granularity information maximization theory, we further take advantage of the complementary information from different neighborhood sizes via a multi-granularity fusion to obtain the most discriminative and stable features. For validation, we compare our method with six popular feature selection methods using three public omics datasets as well as resting-state fMRI data of 393 SZ patients and 429 healthy controls. Results show that our method obtained higher classification accuracies on both omics data (100.0%, 88.6%, and 72.2% for three omics datasets, respectively) and fMRI data (93.9% for main dataset, and 76.3% and 83.8% for two independent datasets, respectively). Moreover, our findings reveal biologically meaningful substrates of SZ, notably involving the connectivity between the thalamus and superior temporal gyrus as well as between the postcentral gyrus and calcarine gyrus. Taken together, we propose a new NRS-based feature selection method that shows the potential of exploring effective and sparse neuroimaging-based biomarkers of mental disorders.

Deep multimodal predictome for studying mental disorders

Characterizing neuropsychiatric disorders is challenging due to heterogeneity in the population. We propose combining structural and functional neuroimaging and genomic data in a multimodal classification framework to leverage their complementary information. Our objectives are two-fold (i) to improve the classification of disorders and (ii) to introspect the concepts learned to explore underlying neural and biological mechanisms linked to mental disorders. Previous multimodal studies have focused on naïve neural networks, mostly perceptron, to learn modality-wise features and often assume equal contribution from each modality. Our focus is on the development of neural networks for feature learning and implementing an adaptive control unit for the fusion phase. Our mid fusion with attention model includes a multilayer feed-forward network, an autoencoder, a bi-directional long short-term memory unit with attention as the features extractor, and a linear attention module for controlling modality-specific influence. The proposed model acquired 92% (p < .0001) accuracy in schizophrenia prediction, outperforming several other state-of-the-art models applied to unimodal or multimodal data. Post hoc feature analyses uncovered critical neural features and genes/biological pathways associated with schizophrenia. The proposed model effectively combines multimodal neuroimaging and genomics data for predicting mental disorders. Interpreting salient features identified by the model may advance our understanding of their underlying etiological mechanisms.

Multi-Modal Imaging Genetics Data Fusion via a Hypergraph-Based Manifold Regularization: Application to Schizophrenia Study

Recent studies show that multi-modal data fusion techniques combine information from diverse sources for comprehensive diagnosis and prognosis of complex brain disorder, often resulting in improved accuracy compared to single-modality approaches. However, many existing data fusion methods extract features from homogeneous networs, ignoring heterogeneous structural information among multiple modalities. To this end, we propose a Hypergraph-based Multi-modal data Fusion algorithm, namely HMF. Specifically, we first generate a hypergraph similarity matrix to represent the high-order relationships among subjects, and then enforce the regularization term based upon both the inter- and intra-modality relationships of the subjects. Finally, we apply HMF to integrate imaging and genetics datasets. Validation of the proposed method is performed on both synthetic data and real samples from schizophrenia study. Results show that our algorithm outperforms several competing methods, and reveals significant interactions among risk genes, environmental factors and abnormal brain regions.

The alterations of brain functional connectivity networks in major depressive disorder detected by machine learning through multisite rs-fMRI data

BACKGROUND

The current diagnosis of major depressive disorder (MDD) is mainly based on the patient's self-report and clinical symptoms. Machine learning methods are used to identify MDD using resting-state functional magnetic resonance imaging (rs-fMRI) data. However, due to large site differences in multisite rs-fMRI data and the difficulty of sample collection, most of the current machine learning studies use small sample sizes of rs-fMRI datasets to detect the alterations of functional connectivity (FC) or network attribute (NA), which may affect the reliability of the experimental results.

METHODS

Multisite rs-fMRI data were used to increase the size of the sample, and then we extracted the functional connectivity (FC) and network attribute (NA) features from 1611 rs-fMRI data (832 patients with MDD (MDDs) and 779 healthy controls (HCs)). ComBat algorithm was used to harmonize the data variances caused by the multisite effect, and multivariate linear regression was used to remove age and sex covariates. Two-sample t-test and wrapper-based feature selection methods (support vector machine recursive feature elimination with cross-validation (SVM-RFECV) and LightGBM's "feature_importances_" function) were used to select important features. The Shapley additive explanations (SHAP) method was used to assign the contribution of features to the best classification effect model.

RESULTS

The best result was obtained from the LinearSVM model trained with the 136 important features selected by SVMRFE-CV. In the nested five-fold cross-validation (consisting of an outer and an inner loop of five-fold cross-validation) of 1611 data, the model achieved the accuracy, sensitivity, and specificity of 68.90 %, 71.75 %, and 65.84 %, respectively. The 136 important features were tested in a small dataset and obtained excellent classification results after balancing the ratio between patients with depression and HCs.

CONCLUSIONS

The combined use of FC and NA features is effective for classifying MDDs and HCs. The important FC and NA features extracted from the large sample dataset have some generalization performance and may be used as a reference for the altered brain functional connectivity networks in MDD.

Distinguishing between depression in bipolar disorder and unipolar depression using magnetic resonance imaging: a systematic review

OBJECTIVES

Magnetic resonance imaging (MRI) studies comparing bipolar and unipolar depression characterize pathophysiological differences between these conditions. However, it is difficult to interpret the current literature due to differences in MRI modalities, analysis methods, and study designs.

METHODS

We conducted a systematic review of publications using MRI to compare individuals with bipolar and unipolar depression. We grouped studies according to MRI modality and task design. Within the discussion, we critically evaluated and summarized the functional MRI research and then further complemented these findings by reviewing the structural MRI literature.

RESULTS

We identified 88 MRI publications comparing participants with bipolar depression and unipolar depressive disorder. Compared to individuals with unipolar depression, participants with bipolar disorder exhibited heightened function, increased within network connectivity, and reduced grey matter volume in salience and central executive network brain regions. Group differences in default mode network function were less consistent but more closely associated with depressive symptoms in participants with unipolar depression but distractibility in bipolar depression.

CONCLUSIONS

When comparing mood disorder groups, the neuroimaging evidence suggests that individuals with bipolar disorder are more influenced by emotional and sensory processing when responding to their environment. In contrast, depressive symptoms and neurofunctional response to emotional stimuli were more closely associated with reduced central executive function and less adaptive cognitive control of emotionally oriented brain regions in unipolar depression. Researchers now need to replicate and refine network-level trends in these heterogeneous mood disorders and further characterize MRI markers associated with early disease onset, progression, and recovery.

Neural substrates of motivational dysfunction across neuropsychiatric conditions: Evidence from meta-analysis and lesion network mapping

Motivational dysfunction constitutes one of the fundamental dimensions of psychopathology cutting across traditional diagnostic boundaries. However, it is unclear whether there is a common neural circuit responsible for motivational dysfunction across neuropsychiatric conditions. To address this issue, the current study combined a meta-analysis on psychiatric neuroimaging studies of reward/loss anticipation and consumption (4308 foci, 438 contrasts, 129 publications) with a lesion network mapping approach (105 lesion cases). Our meta-analysis identified transdiagnostic hypoactivation in the ventral striatum (VS) for clinical/at-risk conditions compared to controls during the anticipation of both reward and loss. Moreover, the VS subserves a key node in a distributed brain network which encompasses heterogeneous lesion locations causing motivation-related symptoms. These findings do not only provide the first meta-analytic evidence of shared neural alternations linked to anticipatory motivation-related deficits, but also shed novel light on the role of VS dysfunction in motivational impairments in terms of both network integration and psychological functions. Particularly, the current findings suggest that motivational dysfunction across neuropsychiatric conditions is rooted in disruptions of a common brain network anchored in the VS, which contributes to motivational salience processing rather than encoding positive incentive values.

Predicting the future of neuroimaging predictive models in mental health

Predictive modeling using neuroimaging data has the potential to improve our understanding of the neurobiology underlying psychiatric disorders and putatively information interventions. Accordingly, there is a plethora of literature reviewing published studies, the mathematics underlying machine learning, and the best practices for using these approaches. As our knowledge of mental health and machine learning continue to evolve, we instead aim to look forward and "predict" topics that we believe will be important in current and future studies. Some of the most discussed topics in machine learning, such as bias and fairness, the handling of dirty data, and interpretable models, may be less familiar to the broader community using neuroimaging-based predictive modeling in psychiatry. In a similar vein, transdiagnostic research and targeting brain-based features for psychiatric intervention are modern topics in psychiatry that predictive models are well-suited to tackle. In this work, we target an audience who is a researcher familiar with the fundamental procedures of machine learning and who wishes to increase their knowledge of ongoing topics in the field. We aim to accelerate the utility and applications of neuroimaging-based predictive models for psychiatric research by highlighting and considering these topics. Furthermore, though not a focus, these ideas generalize to neuroimaging-based predictive modeling in other clinical neurosciences and predictive modeling with different data types (e.g., digital health data).

Clinical prediction models in psychiatry: a systematic review of two decades of progress and challenges

Recent years have seen the rapid proliferation of clinical prediction models aiming to support risk stratification and individualized care within psychiatry. Despite growing interest, attempts to synthesize current evidence in the nascent field of precision psychiatry have remained scarce. This systematic review therefore sought to summarize progress towards clinical implementation of prediction modeling for psychiatric outcomes. We searched MEDLINE, PubMed, Embase, and PsychINFO databases from inception to September 30, 2020, for English-language articles that developed and/or validated multivariable models to predict (at an individual level) onset, course, or treatment response for non-organic psychiatric disorders (PROSPERO: CRD42020216530). Individual prediction models were evaluated based on three key criteria: (i) mitigation of bias and overfitting; (ii) generalizability, and (iii) clinical utility. The Prediction model Risk Of Bias ASsessment Tool (PROBAST) was used to formally appraise each study's risk of bias. 228 studies detailing 308 prediction models were ultimately eligible for inclusion. 94.5% of developed prediction models were deemed to be at high risk of bias, largely due to inadequate or inappropriate analytic decisions. Insufficient internal validation efforts (within the development sample) were also observed, while only one-fifth of models underwent external validation in an independent sample. Finally, our search identified just one published model whose potential utility in clinical practice was formally assessed. Our findings illustrated significant growth in precision psychiatry with promising progress towards real-world application. Nevertheless, these efforts have been inhibited by a preponderance of bias and overfitting, while the generalizability and clinical utility of many published models has yet to be formally established. Through improved methodological rigor during initial development, robust evaluations of reproducibility via independent validation, and evidence-based implementation frameworks, future research has the potential to generate risk prediction tools capable of enhancing clinical decision-making in psychiatric care.

Classification of Parkinson's disease using a region-of-interest- and resting-state functional magnetic resonance imaging-based radiomics approach

To investigate the value of combining amplitude of low-frequency fluctuations-based radiomics and the support vector machine classifier method in distinguishing patients with Parkinson's disease from healthy controls. A total of 123 patients with Parkinson's disease and 90 healthy controls from three centers with functional and structural MRI images were included in this study. We extracted radiomics features using the Brainnetome 246 atlas from the mean amplitude of low-frequency fluctuations maps. Two-sample t-tests and recursive feature elimination combined with support vector machine method were applied for feature selection and dimensionality reduction. We used support vector machine classifier to construct model and identify the discriminative features. The automated anatomical labeling 90 atlas and fivefold cross-validation were used to evaluate the robustness and generalization of the classifier. We found our model obtained a high classification performance with an accuracy of 78.07%, and AUC, sensitivity, and specificity of 0.8597, 78.80%, and 76.08%, respectively. We detected 7 discriminative brain subregions. The fivefold cross-validation and automated anatomical labeling 90 atlas also got high classification accuracy, and we found Brainnetome 246 atlas achieved a higher classification performance than the automated anatomical labeling 90 atlas both with tenfold and fivefold cross-validation. Our findings may help the early diagnosis of Parkinson's disease and provide support for research on Parkinson's disease mechanisms and clinical evaluation.

Robustness of individualized inferences from longitudinal resting state EEG dynamics

Tracking how individual human brains change over extended timescales is crucial to clinical scenarios ranging from stroke recovery to healthy aging. The use of resting state (RS) activity for tracking is a promising possibility. However, it is unresolved how a person's RS activity over time can be decoded to distinguish neurophysiological changes from confounding cognitive variability. Here, we develop a method to screen RS activity changes for these confounding effects by formulating it as a problem of change classification. We demonstrate a novel solution to change classification by linking individual-specific change to inter-individual differences. Individual RS-EEG was acquired over five consecutive days including task states devised to simulate the effects of inter-day cognitive variation. As inter-individual differences are shaped by neurophysiological differences, the inter-individual differences in RS activity on one day were analyzed (using machine learning) to identify distinctive configurations in each individual's RS activity. Using this configuration as a decision-rule, an individual could be re-identified from 2-second samples of the instantaneous oscillatory power spectrum acquired on a different day both from RS and confounded-RS with a limited loss in accuracy. Importantly, the low loss in accuracy in cross-day vs same-day classification was achieved with classifiers that combined information from multiple frequency bands at channels across the scalp (with a concentration at characteristic fronto-central and occipital zones). Taken together, these findings support the technical feasibility of screening RS activity for confounding effects and the suitability of longitudinal RS for robust individualized inferences about neurophysiological change in health and disease.

Exposure of Child Maltreatment Leads to a Risk of Mental Illness and Poor Prognosis in Taiwan: A Nationwide Cohort Study from 2000 to 2015

Objective: To investigate whether children with maltreatment exposure were associated with the risk of psychiatric disorders, suicide, and death. Methods: A retrospective cohort study was conducted, with 1592 child maltreatment cases and 6368 comparison cohort (1:4) matched for gender, age, and index year, from the Longitudinal Generation Tracking Database (LGTD2000) sampled from Taiwan National Health Insurance Research Database (NHIRD) in 2000, backtracking between 2000−2015 in Taiwan. The stratified Cox regression model was used to compare the risk of developing a mental illness and poor prognosis during the 15 years of follow-up. Results: There were 473 in the cohort with child maltreatment (675.10 cases per 100,000 person years) and 1289 in the comparison cohort (453.82 cases per 100,000 person years) that developed mental illness and poor prognosis. The stratified Cox regression model revealed that the adjusted hazard ratio (HR) was 1.91 to 11.76 (p < 0.05) after adjusting for monthly income level, occupation, and CCI after violence. Conclusion: Exposure to child maltreatment is associated with the risk of psychiatric disorders, but not suicide or death. This finding could be a reminder for clinicians about the mental health problems in patients with child maltreatment.

Neuroimaging of psychiatric disorders

Psychiatry remains the only medical specialty where diagnoses are still based on clinical syndromes rather than measurable biological abnormalities. As imaging technology and analytical methods evolve, it is becoming clear that subtle but measurable radiological characteristics exist and can be used to experimentally classify psychiatric disorders, predict response to treatment and, hopefully, develop new, more effective therapies. This review highlights advances in neuroimaging modalities that are now allowing assessment of brain structure, connectivity and neural network function, describes technical aspects of the most promising methods, and summarizes observations made in some frequent psychiatric disorders.

Individual-specific networks for prediction modelling - A scoping review of methods

BACKGROUND

Recent advances in biotechnology enable the acquisition of high-dimensional data on individuals, posing challenges for prediction models which traditionally use covariates such as clinical patient characteristics. Alternative forms of covariate representations for the features derived from these modern data modalities should be considered that can utilize their intrinsic interconnection. The connectivity information between these features can be represented as an individual-specific network defined by a set of nodes and edges, the strength of which can vary from individual to individual. Global or local graph-theoretical features describing the network may constitute potential prognostic biomarkers instead of or in addition to traditional covariates and may replace the often unsuccessful search for individual biomarkers in a high-dimensional predictor space.

METHODS

We conducted a scoping review to identify, collate and critically appraise the state-of-art in the use of individual-specific networks for prediction modelling in medicine and applied health research, published during 2000-2020 in the electronic databases PubMed, Scopus and Embase.

RESULTS

Our scoping review revealed the main application areas namely neurology and pathopsychology, followed by cancer research, cardiology and pathology (N = 148). Network construction was mainly based on Pearson correlation coefficients of repeated measurements, but also alternative approaches (e.g. partial correlation, visibility graphs) were found. For covariates measured only once per individual, network construction was mostly based on quantifying an individual's contribution to the overall group-level structure. Despite the multitude of identified methodological approaches for individual-specific network inference, the number of studies that were intended to enable the prediction of clinical outcomes for future individuals was quite limited, and most of the models served as proof of concept that network characteristics can in principle be useful for prediction.

CONCLUSION

The current body of research clearly demonstrates the value of individual-specific network analysis for prediction modelling, but it has not yet been considered as a general tool outside the current areas of application. More methodological research is still needed on well-founded strategies for network inference, especially on adequate network sparsification and outcome-guided graph-theoretical feature extraction and selection, and on how networks can be exploited efficiently for prediction modelling.

Role of Brain Imaging in Drug Development for Psychiatry

Background:

Over the last decades, many brain imaging studies have contributed to new insights in the pathogenesis of psychiatric disease. However, in spite of these developments, progress in the development of novel therapeutic drugs for prevalent psychiatric health conditions has been limited.

Objective:

In this review, we discuss translational, diagnostic and methodological issues that have hampered drug development in CNS disorders with a particular focus on psychiatry. The role of preclinical models is critically reviewed and opportunities for brain imaging in early stages of drug development using PET and fMRI are discussed. The role of PET and fMRI in drug development is reviewed emphasizing the need to engage in collaborations between industry, academia and phase I units.

Conclusion:

Brain imaging technology has revolutionized the study of psychiatric illnesses, and during the last decade, neuroimaging has provided valuable insights at different levels of analysis and brain organization, such as effective connectivity (anatomical), functional connectivity patterns and neurochemical information that may support both preclinical and clinical drug development. Since there is no unifying pathophysiological theory of individual psychiatric syndromes and since many symptoms cut across diagnostic boundaries, a new theoretical framework has been proposed that may help in defining new targets for treatment and thus enhance drug development in CNS diseases. In addition, it is argued that new proposals for data-mining and mathematical modelling as well as freely available databanks for neural network and neurochemical models of rodents combined with revised psychiatric classification will lead to new validated targets for drug development.

Machine learning approaches for prediction of bipolar disorder based on biological, clinical and neuropsychological markers: a systematic review and meta-analysis

Applying machine learning (ML) to objective markers may overcome prognosis uncertainty due to the subjective nature of the diagnosis of bipolar disorder (BD). This PRISMA-compliant meta-analysis provides new systematic evidence of the BD classification accuracy reached by different markers and ML algorithms. We focused on neuroimaging, electrophysiological techniques, peripheral biomarkers, genetic data, neuropsychological or clinical measures, and multimodal approaches. PubMed, Embase and Scopus were searched through 3^rd December 2020. Meta-analyses were performed using random-effect models. Overall, 81 studies were included in this systematic review and 65 in the meta-analysis (11,336 participants, 3,903 BD). The overall pooled classification accuracy was 0.77 (95%CI[0.75;0.80]). Despite subgroup analyses for diagnostic comparison group, psychiatric disorders, marker, ML algorithm, and validation procedure were not significant, linear discriminant analysis significantly outperformed support vector machine for peripheral biomarkers (p=0.03). Sample size was inversely related to accuracy. Evidence of publication bias was detected. Ultimately, although ML reached a high accuracy in differentiating BD from other psychiatric disorders, best practices in methodology are needed for the advancement of future studies.

Evaluating the Performance of Machine Learning Models for Automatic Diagnosis of Patients with Schizophrenia Based on a Single Site Dataset of 440 Participants

Background

Methods

Results

Conclusions

State-related neural influences on fMRI connectivity estimation

The spatiotemporal structure of functional magnetic resonance imaging (fMRI) signals has provided a valuable window into the network underpinnings of human brain function and dysfunction. Although some cross-regional temporal correlation patterns (functional connectivity; FC) exhibit a high degree of stability across individuals and species, there is growing acknowledgment that measures of FC can exhibit marked changes over a range of temporal scales. Further, FC can covary with experimental task demands and ongoing neural processes linked to arousal, consciousness and perception, cognitive and affective state, and brain-body interactions. The increased recognition that such interrelated neural processes modulate FC measurements has raised both challenges and new opportunities in using FC to investigate brain function. Here, we review recent advances in the quantification of neural effects that shape fMRI FC and discuss the broad implications of these findings in the design and analysis of fMRI studies. We also discuss how a more complete understanding of the neural factors that shape FC measurements can resolve apparent inconsistencies in the literature and lead to more interpretable conclusions from fMRI studies.

Scarcity Mindset Neuro Network Decoding With Reward: A Tree-Based Model and Functional Near-Infrared Spectroscopy Study

Resource scarcity imposes challenging demands on the human cognitive system. Insufficient resources cause the scarcity mindset to affect cognitive performance, while reward enhances cognitive function. Here, we examined how reward and scarcity simultaneously contribute to cognitive performance. Experimental manipulation to induce a polar scarcity mindset and reward conditions within participants under functional near-infrared spectroscopy (fNIRS) recording was implemented to explore the mechanism underlying the scarcity mindset and reward in terms of behavior and neurocognition. Participants showed decreased functional connectivity from the dorsolateral prefrontal cortex (DLPFC) to the ventrolateral prefrontal cortex (VLPFC) with a scarcity mindset, a region often implicated in cognitive control. Moreover, under reward conditions, the brain activation of the maximum total Hb bold signal was mainly located in the left hemisphere [channels 1, 3, and 4, left ventrolateral prefrontal cortex (L-VLPFC) and channel 6, left dorsolateral prefrontal cortex (L-DLPFC)], and there was also significant brain activation of the right dorsolateral prefrontal cortex (R-DLPFC) in the right hemisphere (channel 17). Furthermore, these data indicate the underlying neural changes of the scarcity mentality and demonstrate that brain activities may underlie reward processing. Additionally, the base-tree machine learning model was trained to detect the mechanism of reward function in the prefrontal cortex (PFC). According to SHapley Additive exPlanations (SHAP), channel 8 contributed the most important effect, as well as demonstrating a high-level interrelationship with other channels.

Multi-modal deep learning of functional and structural neuroimaging and genomic data to predict mental illness

Neuropsychiatric disorders such as schizophrenia are very heterogeneous in nature and typically diagnosed using self-reported symptoms. This makes it difficult to pose a confident prediction on the cases and does not provide insight into the underlying neural and biological mechanisms of these disorders. Combining neuroimaging and genomic data with a multi-modal 'predictome' paves the way for biologically informed markers and may improve prediction reliability. With that, we develop a multi-modal deep learning framework by fusing data from different modalities to capture the interaction between the latent features and evaluate their complementary information in characterizing schizophrenia. Our deep model uses structural MRI, functional MRI, and genome-wide polymorphism data to perform the classification task. It includes a multi-layer feed-forward network, an encoder, and a long short-term memory (LSTM) unit with attention to learn the latent features and adopt a joint training scheme capturing synergies between the modalities. The hybrid network also uses different regularizers for addressing the inherent overfitting and modality-specific bias in the multi-modal setup. Next, we run the network through a saliency model to analyze the learned features. Integrating modalities enhances the performance of the classifier, and our framework acquired 88% (P < 0.0001) accuracy on a dataset of 437 subjects. The trimodal accuracy is comparable to the state-of-the-art performance on a data collection of this size and outperforms the unimodal and bimodal baselines we compared. Model introspection was used to expose the salient neural features and genes/biological pathways associated with schizophrenia. To our best knowledge, this is the first approach that fuses genomic information with structural and functional MRI biomarkers for predicting schizophrenia. We believe this type of modality blending can better explain the disorder's dynamics by adding cross-modal prospects.Clinical Relevance- This study combinedly learns imaging and genomic features for the classification of schizophrenia. The data fusion scheme extracts modality interactions, and the saliency experiments report multiple functional and structural networks closely connected to the disorder.

Using deep learning to classify pediatric posttraumatic stress disorder at the individual level

BACKGROUND

Children exposed to natural disasters are vulnerable to developing posttraumatic stress disorder (PTSD). Previous studies using resting-state functional neuroimaging have revealed alterations in graph-based brain topological network metrics in pediatric PTSD patients relative to healthy controls (HC). Here we aimed to apply deep learning (DL) models to neuroimaging markers of classification which may be of assistance in diagnosis of pediatric PTSD.

METHODS

We studied 33 pediatric PTSD and 53 matched HC. Functional connectivity between 90 brain regions from the automated anatomical labeling atlas was established using partial correlation coefficients, and the whole-brain functional connectome was constructed by applying a threshold to the resultant 90 * 90 partial correlation matrix. Graph theory analysis was used to examine the topological properties of the functional connectome. A DL algorithm then used this measure to classify pediatric PTSD vs HC.

RESULTS

Graphic topological measures using DL provide a potentially clinically useful classifier for differentiating pediatric PTSD and HC (overall accuracy 71.2%). Frontoparietal areas (central executive network), cingulate cortex, and amygdala contributed the most to the DL model's performance.

CONCLUSIONS

Graphic topological measures based on fMRI data could contribute to imaging models of clinical utility in distinguishing pediatric PTSD from HC. DL model may be a useful tool in the identification of brain mechanisms PTSD participants.

Brain connectivity dynamics in cisgender and transmen people with gender incongruence before gender affirmative hormone treatment

Large-scale brain network interactions have been described between trans- and cis-gender binary identities. However, a temporal perspective of the brain's spontaneous fluctuations is missing. We investigated the functional connectivity dynamics in transmen with gender incongruence and its relationship with interoceptive awareness. We describe four states in native and meta-state spaces: (i) one state highly prevalent with sparse overall connections; (ii) a second with strong couplings mainly involving components of the salience, default, and executive control networks. Two states with global sparse connectivity but positive couplings (iii) within the sensorimotor network, and (iv) between salience network regions. Transmen had more dynamical fluidity than cismen, while cismen presented less meta-state fluidity and range dynamism than transmen and ciswomen. A positive association between attention regulation and fluidity and meta-state range dynamism was found in transmen. There exist gender differences in the temporal brain dynamism, characterized by distinct interrelations of the salience network as catalyst interacting with other networks. We offer a functional explanation from the neurodevelopmental cortical hypothesis of a gendered-self.

Highlighting psychological pain avoidance and decision-making bias as key predictors of suicide attempt in major depressive disorder-A novel investigative approach using machine learning

OBJECTIVE

Predicting suicide is notoriously difficult and complex, but a serious public health issue. An innovative approach utilizing machine learning (ML) that incorporates features of psychological mechanisms and decision-making characteristics related to suicidality could create an improved model for identifying suicide risk in patients with major depressive disorder (MDD).

METHOD

Forty-four patients with MDD and past suicide attempts (MDD_SA, N = 44); 48 patients with MDD but without past suicide attempts (MDD_NS, N = 48-42 of whom with suicide ideation [MDD_SI, N = 42]), and healthy controls (HCs, N = 51) completed seven psychometric assessments including the Three-dimensional Psychological Pain Scale (TDPPS), and one behavioral assessment, the Balloon Analogue Risk Task (BART). Descriptive statistics, group comparisons, logistic regressions, and ML were used to explore and compare the groups and generate predictors of suicidal acts.

RESULTS

MDD_SA and MDD_NS differed in TDPPS total score, pain arousal and avoidance subscale scores, suicidal ideation scores, and relevant decision-making indicators in BART. Logistic regression tests linked suicide attempts to psychological pain avoidance and a risk decision-making indicator. The resultant key ML model distinguished MDD_SA/MDD_NS with 88.2% accuracy. The model could also distinguish MDD_SA/MDD_SI with 81.25% accuracy. The ML model using hopelessness could classify MDD_SI/HC with 94.4% accuracy.

CONCLUSION

ML analyses showed that motivation to avoid intolerable psychological pain, coupled with impaired decision-making bias toward under-valuing life's worth are highly predictive of suicide attempts. Analyses also demonstrated that suicidal ideation and attempts differed in potential mechanisms, as suicidal ideation was more related to hopelessness. ML algorithms show useful promises as a predictive instrument.

The Monash Autism-ADHD genetics and neurodevelopment (MAGNET) project design and methodologies: a dimensional approach to understanding neurobiological and genetic aetiology

Background

ASD and ADHD are prevalent neurodevelopmental disorders that frequently co-occur and have strong evidence for a degree of shared genetic aetiology. Behavioural and neurocognitive heterogeneity in ASD and ADHD has hampered attempts to map the underlying genetics and neurobiology, predict intervention response, and improve diagnostic accuracy. Moving away from categorical conceptualisations of psychopathology to a dimensional approach is anticipated to facilitate discovery of data-driven clusters and enhance our understanding of the neurobiological and genetic aetiology of these conditions. The Monash Autism-ADHD genetics and neurodevelopment (MAGNET) project is one of the first large-scale, family-based studies to take a truly transdiagnostic approach to ASD and ADHD. Using a comprehensive phenotyping protocol capturing dimensional traits central to ASD and ADHD, the MAGNET project aims to identify data-driven clusters across ADHD-ASD spectra using deep phenotyping of symptoms and behaviours; investigate the degree of familiality for different dimensional ASD-ADHD phenotypes and clusters; and map the neurocognitive, brain imaging, and genetic correlates of these data-driven symptom-based clusters.

Methods

The MAGNET project will recruit 1,200 families with children who are either typically developing, or who display elevated ASD, ADHD, or ASD-ADHD traits, in addition to affected and unaffected biological siblings of probands, and parents. All children will be comprehensively phenotyped for behavioural symptoms, comorbidities, neurocognitive and neuroimaging traits and genetics.

Conclusion

The MAGNET project will be the first large-scale family study to take a transdiagnostic approach to ASD-ADHD, utilising deep phenotyping across behavioural, neurocognitive, brain imaging and genetic measures.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13229-021-00457-3.

Data-driven approaches to neuroimaging biomarkers for neurological and psychiatric disorders: emerging approaches and examples

PURPOSE OF REVIEW

The 'holy grail' of clinical applications of neuroimaging to neurological and psychiatric disorders via personalized biomarkers has remained mostly elusive, despite considerable effort. However, there are many reasons to continue to be hopeful, as the field has made remarkable advances over the past few years, fueled by a variety of converging technical and data developments.

RECENT FINDINGS

We discuss a number of advances that are accelerating the push for neuroimaging biomarkers including the advent of the 'neuroscience big data' era, biomarker data competitions, the development of more sophisticated algorithms including 'guided' data-driven approaches that facilitate automation of network-based analyses, dynamic connectivity, and deep learning. Another key advance includes multimodal data fusion approaches which can provide convergent and complementary evidence pointing to possible mechanisms as well as increase predictive accuracy.

SUMMARY

The search for clinically relevant neuroimaging biomarkers for neurological and psychiatric disorders is rapidly accelerating. Here, we highlight some of these aspects, provide recent examples from studies in our group, and link to other ongoing work in the field. It is critical that access and use of these advanced approaches becomes mainstream, this will help propel the community forward and facilitate the production of robust and replicable neuroimaging biomarkers.

Brain imaging-based machine learning in autism spectrum disorder: methods and applications

Autism spectrum disorder (ASD) is a neurodevelopmental condition with early childhood onset and high heterogeneity. As the pathogenesis is still elusive, ASD diagnosis is comprised of a constellation of behavioral symptoms. Non-invasive brain imaging techniques, such as magnetic resonance imaging (MRI), provide a valuable objective measurement of the brain. Many efforts have been devoted to developing imaging-based diagnostic tools for ASD based on machine learning (ML) technologies. In this survey, we review recent advances that utilize machine learning approaches to classify individuals with and without ASD. First, we provide a brief overview of neuroimaging-based ASD classification studies, including the analysis of publications and general classification pipeline. Next, representative studies are highlighted and discussed in detail regarding different imaging modalities, methods and sample sizes. Finally, we highlight several common challenges and provide recommendations on future directions. In summary, identifying discriminative biomarkers for ASD diagnosis is challenging, and further establishing more comprehensive datasets and dissecting the individual and group heterogeneity will be critical to achieve better ADS diagnosis performance. Machine learning methods will continue to be developed and are poised to help advance the field in this regard.

Implications from translational cross-validation of clinical assessment tools for diagnosis and treatment in psychiatry

Traditional therapeutic methods in psychiatry, such as psychopharmacology and psychotherapy help many people suffering from mental disorders, but in the long-term prove to be effective in a relatively small proportion of those affected. Therapeutically, resistant forms of mental disorders such as schizophrenia, major depressive disorder, and bipolar disorder lead to persistent distress and dysfunction in personal, social, and professional aspects. In an effort to address these problems, the translational approach in neuroscience has initiated the inclusion of novel or modified unconventional diagnostic and therapeutic techniques with promising results. For instance, neuroimaging data sets from multiple modalities provide insight into the nature of pathophysiological mechanisms such as disruptions of connectivity, integration, and segregation of neural networks, focusing on the treatment of mental disorders through instrumental biomedical methods such as electro-convulsive therapy (ECT), transcranial magnetic stimulation (TMS), transcranial direct current stimulation (tDCS) and deep brain stimulation (DBS). These methodologies have yielded promising results that have yet to be understood and improved to enhance the prognosis of the severe and persistent psychotic and affective disorders. The current review is focused on the translational approach in the management of schizophrenia and mood disorders, as well as the adaptation of new transdisciplinary diagnostic tools such as neuroimaging with concurrently administered psychopathological questionnaires and integration of the results into the therapeutic framework using various advanced instrumental biomedical tools such as ECT, TMS, tDCS and DBS.

Machine Learning Identifies Metabolic Signatures that Predict the Risk of Recurrent Angina in Remitted Patients after Percutaneous Coronary Intervention: A Multicenter Prospective Cohort Study

Recurrent angina (RA) after percutaneous coronary intervention (PCI) has few known risk factors, hampering the identification of high-risk populations. In this multicenter study, plasma samples are collected from patients with stable angina after PCI, and these patients are followed-up for 9 months for angina recurrence. Broad-spectrum metabolomic profiling with LC-MS/MS followed by multiple machine learning algorithms is conducted to identify the metabolic signatures associated with future risk of angina recurrence in two large cohorts (n = 750 for discovery set, and n = 775 for additional independent discovery cohort). The metabolic predictors are further validated in a third cohort from another center (n = 130) using a clinically-sound quantitative approach. Compared to angina-free patients, the remitted patients with future RA demonstrates a unique chemical endophenotype dominated by abnormalities in chemical communication across lipid membranes and mitochondrial function. A novel multi-metabolite predictive model constructed from these latent signatures can stratify remitted patients at high-risk for angina recurrence with over 89% accuracy, sensitivity, and specificity across three independent cohorts. Our findings revealed reproducible plasma metabolic signatures to predict patients with a latent future risk of RA during post-PCI remission, allowing them to be treated in advance before an event.

Exploring Dynamic Connectivity Biomarkers of Neuropsychiatric Disorders

A recent study by Lee et al. showed that a dynamic functional connectivity pattern induced by tonic experimental pain might serve as a biomarker of chronic pain. The study illustrates key topics in translational neuroscience: the differentiation of biomarker functions, the multimodal integration of biomarkers, and the functional relevance of dynamic connectivity.

Neuroimaging in attention-deficit/hyperactivity disorder

PURPOSE OF REVIEW

Neuroimaging research on attention-deficit/hyperactivity disorder (ADHD) continues growing in extent and complexity, although it has yet to become clinically meaningful. We review recent MRI research on ADHD, to identify robust findings, current trends and challenges.

RECENT FINDINGS

We identified 40 publications between January 2019 and September 2020 reporting or reviewing MRI research on ADHD. Four meta-analyses have presented conflicting results regarding across-study convergence of functional and resting-state functional (fMRI and R-fMRI) studies on ADHD. On the other hand, the Enhancing NeuroImaging Genetics Through Meta-Analysis international consortium has identified statistically robust albeit small differences in structural brain cortical and subcortical indices in children with ADHD versus typically developing controls. Other international consortia are harnessing open-science efforts and multimodal data (imaging, genetics, phenotypic) to shed light on the complex interplay of genetics, environment, and development in the pathophysiology of ADHD. We note growing research in 'prediction' science, which applies machine-learning analysis to identify biomarkers of disease based on big data.

SUMMARY

Neuroimaging in ADHD is still far from informing clinical practice. Current large-scale, multimodal, and open-science initiatives represent promising paths toward untangling the neurobiology of ADHD.

Great Expectations: A Critical Review of and Suggestions for the Study of Reward Processing as a Cause and Predictor of Depression

Both human and animal studies support the relationship between depression and reward processing abnormalities, giving rise to the expectation that neural signals of these processes may serve as biomarkers or mechanistic treatment targets. Given the great promise of this research line, we scrutinized those findings and the theoretical claims that underlie them. To achieve this, we applied the framework provided by classical work on causality as well as contemporary approaches to prediction. We identified a number of conceptual, practical, and analytical challenges to this line of research and used a preregistered meta-analysis to quantify the longitudinal associations between reward processing abnormalities and depression. We also investigated the impact of measurement error on reported data. We found that reward processing abnormalities do not reach levels that would be useful for clinical prediction, yet the available evidence does not preclude a possible causal role in depression.

Multimodal MRI assessment for first episode psychosis: A major change in the thalamus and an efficient stratification of a subgroup

Multi‐institutional brain imaging studies have emerged to resolve conflicting results among individual studies. However, adjusting multiple variables at the technical and cohort levels is challenging. Therefore, it is important to explore approaches that provide meaningful results from relatively small samples at institutional levels. We studied 87 first episode psychosis (FEP) patients and 62 healthy subjects by combining supervised integrated factor analysis (SIFA) with a novel pipeline for automated structure‐based analysis, an efficient and comprehensive method for dimensional data reduction that our group recently established. We integrated multiple MRI features (volume, DTI indices, resting state fMRI—rsfMRI) in the whole brain of each participant in an unbiased manner. The automated structure‐based analysis showed widespread DTI abnormalities in FEP and rs‐fMRI differences between FEP and healthy subjects mostly centered in thalamus. The combination of multiple modalities with SIFA was more efficient than the use of single modalities to stratify a subgroup of FEP (individuals with schizophrenia or schizoaffective disorder) that had more robust deficits from the overall FEP group. The information from multiple MRI modalities and analytical methods highlighted the thalamus as significantly abnormal in FEP. This study serves as a proof‐of‐concept for the potential of this methodology to reveal disease underpins and to stratify populations into more homogeneous sub‐groups.

Deep learning approaches for neural decoding across architectures and recording modalities

Decoding behavior, perception or cognitive state directly from neural signals is critical for brain-computer interface research and an important tool for systems neuroscience. In the last decade, deep learning has become the state-of-the-art method in many machine learning tasks ranging from speech recognition to image segmentation. The success of deep networks in other domains has led to a new wave of applications in neuroscience. In this article, we review deep learning approaches to neural decoding. We describe the architectures used for extracting useful features from neural recording modalities ranging from spikes to functional magnetic resonance imaging. Furthermore, we explore how deep learning has been leveraged to predict common outputs including movement, speech and vision, with a focus on how pretrained deep networks can be incorporated as priors for complex decoding targets like acoustic speech or images. Deep learning has been shown to be a useful tool for improving the accuracy and flexibility of neural decoding across a wide range of tasks, and we point out areas for future scientific development.