Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group

Machine learning with multiple modalities of brain magnetic resonance imaging data to identify the presence of bipolar disorder

BACKGROUND

Bipolar disorder (BD) is a chronic psychiatric mood disorder that is solely diagnosed based on clinical symptoms. These symptoms often overlap with other psychiatric disorders. Efforts to use machine learning (ML) to create predictive models for BD based on data from brain imaging are expanding but have often been limited using only a single modality and the exclusion of the cerebellum, which may be relevant in BD.

METHODS

In this study, we sought to improve ML classification of BD by combining information from structural, functional, and diffusion-weighted imaging. Participants (108 BD I, 78 control) with BD type I and matched controls were recruited into an imaging study. This dataset was randomly divided into training and testing sets. For each of the three modalities, a separate ML model was selected, trained, and then used to generate a prediction of the class of each test subject. Majority voting was used to combine results from the three models to make a final prediction of whether a subject had BD. An independent replication sample was used to evaluate the ability of the ML classification to generalize to data collected at other sites.

RESULTS

Combining the three machine learning models through majority voting resulted in an accuracy of 89.5 % for classification of the test subjects as being in the BD or control group. Bootstrapping resulted in a 95 % confidence interval of 78.9 %-97.4 % for test accuracy. Performance was reduced when only using 2 of the 3 modalities. Analysis of feature importance revealed that the cerebellum and nodes of the emotional control network were among the most important regions for classification. The machine learning model performed at chance on the independent replication sample.

CONCLUSION

BD I could be identified with high accuracy in our relatively small sample by combining structural, functional, and diffusion-weighted imaging data within a single site but not generalize well to an independent replication sample. Future studies using harmonized imaging protocols may facilitate generalization of ML models.

A generalizable normative deep autoencoder for brain morphological anomaly detection: application to the multi-site StratiBip dataset on bipolar disorder in an external validation framework

The heterogeneity of psychiatric disorders makes researching disorder-specific neurobiological markers an ill-posed problem. Here, we face the need for disease stratification models by presenting a generalizable multivariate normative modelling framework for characterizing brain morphology, applied to bipolar disorder (BD). We employed deep autoencoders in an anomaly detection framework, combined with a confounder removal step integrating training and external validation. The model was trained with healthy control (HC) data from the human connectome project and applied to multi-site external data of HC and BD individuals. We found that brain deviating scores were greater, more heterogeneous, and with increased extreme values in the BD group, with volumes prominently from the basal ganglia, hippocampus and adjacent regions emerging as significantly deviating. Similarly, individual brain deviating maps based on modified z scores expressed higher abnormalities occurrences, but their overall spatial overlap was lower compared to HCs. Our generalizable framework enabled the identification of subject- and group-level brain normative-deviating patterns, a step forward towards the development of more effective and personalized clinical decision support systems and patient stratification in psychiatry.

Multivariate brain-cognition associations in euthymic bipolar disorder

BACKGROUND

People with bipolar disorder (BD) tend to show widespread cognitive impairment compared to healthy controls. Impairments in processing speed (PS), attention and executive function (EF) may represent 'core' impairments that have a role in wider cognitive dysfunction. Cognitive impairments appear to relate to structural brain abnormalities in BD, but whether core deficits are related to particular brain regions is unclear and much of the research on brain-cognition associations is limited by univariate analysis and small samples.

METHODS

Euthymic BD patients (n = 56) and matched healthy controls (n = 26) underwent T1-weighted MRI scans and completed neuropsychological tests of PS, attention and EF. We utilised public datasets to develop normative models of cortical thickness (n = 5977) to generate robust estimations of cortical abnormalities in patients. Canonical correlation analysis was used to assess multivariate brain-cognition associations in BD, controlling for age, sex and premorbid IQ.

RESULTS

BD showed impairments on tests of PS, attention and EF, and abnormal cortical thickness in several brain regions compared to healthy controls. Impairments in tests of PS and EF were most strongly associated with cortical thickness in the left inferior temporal, right entorhinal and right temporal pole areas.

CONCLUSION

Impairments in PS, attention and EF can be observed in euthymic BD and may be related to abnormal cortical thickness in temporal regions. Future research should continue to leverage normative modelling and multivariate methods to examine complex brain-cognition associations in BD. Future research may benefit from exploring covariance between traditional brain structural morphological metrics such as cortical thickness, cortical volume and surface area.

Identifying gray matter alterations in Cushing's disease using machine learning: An interpretable approach

BACKGROUND

Cushing's Disease (CD) is a rare clinical syndrome characterized by excessive secretion of adrenocorticotrophic hormone, leading to significant functional and structural brain alterations as observed in Magnetic Resonance Imaging (MRI). While traditional statistical analysis has been widely employed to investigate these MRI changes in CD, it has lacked the ability to predict individual-level outcomes.

PURPOSE

To address this problem, this paper has proposed an interpretable machine learning (ML) framework, including model-level assessment, feature-level assessment, and biology-level assessment to ensure a comprehensive analysis based on structural MRI of CD.

METHODS

The ML framework has effectively identified the changes in brain regions in the stage of model-level assessment, verified the effectiveness of these altered brain regions to predict CD from normal controls in the stage of feature-level assessment, and carried out a correlation analysis between altered brain regions and clinical symptoms in the stage of biology-level assessment.

RESULTS

The experimental results of this study have demonstrated that the Insula, Fusiform gyrus, Superior frontal gyrus, Precuneus, and the opercular portion of the Inferior frontal gyrus of CD showed significant alterations in brain regions. Furthermore, our study has revealed significant correlations between clinical symptoms and the frontotemporal lobes, insulin, and olfactory cortex, which also have been confirmed by previous studies.

CONCLUSIONS

The ML framework proposed in this study exhibits exceptional potential in uncovering the intricate pathophysiological mechanisms underlying CD, with potential applicability in diagnosing other diseases.

Exploring the potential of representation and transfer learning for anatomical neuroimaging: Application to psychiatry

The perspective of personalized medicine for brain disorders requires efficient learning models for anatomical neuroimaging-based prediction of clinical conditions. There is now a consensus on the benefit of deep learning (DL) in addressing many medical imaging tasks, such as image segmentation. However, for single-subject prediction problems, recent studies yielded contradictory results when comparing DL with Standard Machine Learning (SML) on top of classical feature extraction. Most existing comparative studies were limited in predicting phenotypes of little clinical interest, such as sex and age, and using a single dataset. Moreover, they conducted a limited analysis of the employed image pre-processing and feature selection strategies. This paper extensively compares DL and SML prediction capacity on five multi-site problems, including three increasingly complex clinical applications in psychiatry namely schizophrenia, bipolar disorder, and Autism Spectrum Disorder (ASD) diagnosis. To compensate for the relative scarcity of neuroimaging data on these clinical datasets, we also evaluate three pre-training strategies for transfer learning from brain imaging of the general healthy population: self-supervised learning, generative modeling and supervised learning with age. Overall, we find similar performance between randomly initialized DL and SML for the three clinical tasks and a similar scaling trend for sex prediction. This was replicated on an external dataset. We also show highly correlated discriminative brain regions between DL and linear ML models in all problems. Nonetheless, we demonstrate that self-supervised pre-training on large-scale healthy population imaging datasets (N≈10k), along with Deep Ensemble, allows DL to learn robust and transferable representations to smaller-scale clinical datasets (N≤1k). It largely outperforms SML on 2 out of 3 clinical tasks both in internal and external test sets. These findings suggest that the improvement of DL over SML in anatomical neuroimaging mainly comes from its capacity to learn meaningful and useful abstract representations of the brain anatomy, and it sheds light on the potential of transfer learning for personalized medicine in psychiatry.

Verbal Learning and Memory Deficits across Neurological and Neuropsychiatric Disorders: Insights from an ENIGMA Mega Analysis

Deficits in memory performance have been linked to a wide range of neurological and neuropsychiatric conditions. While many studies have assessed the memory impacts of individual conditions, this study considers a broader perspective by evaluating how memory recall is differentially associated with nine common neuropsychiatric conditions using data drawn from 55 international studies, aggregating 15,883 unique participants aged 15-90. The effects of dementia, mild cognitive impairment, Parkinson's disease, traumatic brain injury, stroke, depression, attention-deficit/hyperactivity disorder (ADHD), schizophrenia, and bipolar disorder on immediate, short-, and long-delay verbal learning and memory (VLM) scores were estimated relative to matched healthy individuals. Random forest models identified age, years of education, and site as important VLM covariates. A Bayesian harmonization approach was used to isolate and remove site effects. Regression estimated the adjusted association of each clinical group with VLM scores. Memory deficits were strongly associated with dementia and schizophrenia (p < 0.001), while neither depression nor ADHD showed consistent associations with VLM scores (p > 0.05). Differences associated with clinical conditions were larger for longer delayed recall duration items. By comparing VLM across clinical conditions, this study provides a foundation for enhanced diagnostic precision and offers new insights into disease management of comorbid disorders.

Predicting depression risk in early adolescence via multimodal brain imaging

Depression is an incapacitating psychiatric disorder with increased risk through adolescence. Among other factors, children with family history of depression have significantly higher risk of developing depression. Early identification of pre-adolescent children who are at risk of depression is crucial for early intervention and prevention. In this study, we used a large longitudinal sample from the Adolescent Brain Cognitive Development (ABCD) Study (2658 participants after imaging quality control, between 9-10 years at baseline), we applied advanced machine learning methods to predict depression risk at the two-year follow-up from the baseline assessment, using a set of comprehensive multimodal neuroimaging features derived from structural MRI, diffusion tensor imaging, and task and rest functional MRI. Prediction performance underwent a rigorous cross-validation method of leave-one-site-out. Our results demonstrate that all brain features had prediction scores significantly better than expected by chance, with brain features from rest-fMRI showing the best classification performance in the high-risk group of participants with parental history of depression (N = 625). Specifically, rest-fMRI features, which came from functional connectomes, showed significantly better classification performance than other brain features. This finding highlights the key role of the interacting elements of the connectome in capturing more individual variability in psychopathology compared to measures of single brain regions. Our study contributes to the effort of identifying biological risks of depression in early adolescence in population-based samples.

Distinguishing schizophrenia and bipolar disorder through a Multiclass Classification model based on multimodal neuroimaging data

This study aimed to identify neural biomarkers for schizophrenia (SZ) and bipolar disorder (BP) by analyzing multimodal neuroimaging. Utilizing data from structural magnetic resonance imaging (sMRI), diffusion tensor imaging (DTI), and resting-state functional magnetic resonance imaging (rs-fMRI), multiclass classification models were created for SZ, BP, and healthy controls (HC). A total of 113 participants (BP: 31, SZ: 39, and HC: 43) were recruited under strict enrollment control, from which 272, 200, and 1875 features were extracted from sMRI, DTI, and rs-fMRI data, respectively. A support vector machine (SVM) with recursive feature elimination (RFE) was employed to build the models using a one-against-one approach and leave-one-out cross-validation, achieving a classification accuracy of 70.8%. The most discriminative features were primarily from rs-fMRI, along with significant findings in sMRI and DTI. Key biomarkers identified included the increased thickness of the left cuneus cortex and decreased regional functional connectivity strength (rFCS) in the left supramarginal gyrus as shared indicators for BP and SZ. Additionally, decreased fractional anisotropy in the left superior fronto-occipital fasciculus was suggested as specific to BP, while decreased rFCS in the left inferior parietal area might serve as a specific biomarker for SZ. These findings underscore the potential of multimodal neuroimaging in distinguishing between BP and SZ and contribute to the understanding of their neural underpinnings.

Large-Scale Neuroimaging of Mental Illness

Neuroimaging has provided important insights into the brain variations related to mental illness. Inconsistencies in prior studies, however, call for methods that lead to more replicable and generalizable brain markers that can reliably predict illness severity, treatment course, and prognosis. A paradigm shift is underway with large-scale international research teams actively pooling data and resources to drive consensus findings and test emerging methods aimed at achieving the goals of precision psychiatry. In parallel with large-scale psychiatric genomics studies, international consortia combining neuroimaging data are mapping the transdiagnostic brain signatures of mental illness on an unprecedented scale. This chapter discusses the major challenges, recent findings, and a roadmap for developing better neuroimaging-based tools and markers for mental illness.

The association between cortical gyrification and sleep in adolescents and young adults

STUDY OBJECTIVES

Healthy sleep is important for adolescent neurodevelopment, and relationships between brain structure and sleep can vary in strength over this maturational window. Although cortical gyrification is increasingly considered a useful index for understanding cognitive and emotional outcomes in adolescence, and sleep is also a strong predictor of such outcomes, we know relatively little about associations between cortical gyrification and sleep. We aimed to identify developmentally invariant (stable across age) or developmentally specific (observed only during discrete age intervals) gyrification-sleep relationships in young people.

METHODS

A total of 252 Neuroimaging and Pediatric Sleep Databank participants (9-26 years; 58.3% female) completed wrist actigraphy and a structural MRI scan. Local gyrification index (lGI) was estimated for 34 bilateral brain regions. Naturalistic sleep characteristics (duration, timing, continuity, and regularity) were estimated from wrist actigraphy. Regularized regression for feature selection was used to examine gyrification-sleep relationships.

RESULTS

For most brain regions, greater lGI was associated with longer sleep duration, earlier sleep timing, lower variability in sleep regularity, and shorter time awake after sleep onset. lGI in frontoparietal network regions showed associations with sleep patterns that were stable across age. However, in default mode network regions, lGI was only associated with sleep patterns from late childhood through early-to-mid adolescence, a period of vulnerability for mental health disorders.

CONCLUSIONS

We detected both developmentally invariant and developmentally specific ties between local gyrification and naturalistic sleep patterns. Default mode network regions may be particularly susceptible to interventions promoting more optimal sleep during childhood and adolescence.

Prediction of estimated risk for bipolar disorder using machine learning and structural MRI features

BACKGROUND

Individuals with bipolar disorder are commonly correctly diagnosed a decade after symptom onset. Machine learning techniques may aid in early recognition and reduce the disease burden. As both individuals at risk and those with a manifest disease display structural brain markers, structural magnetic resonance imaging may provide relevant classification features.

METHODS

Following a pre-registered protocol, we trained linear support vector machine (SVM) to classify individuals according to their estimated risk for bipolar disorder using regional cortical thickness of help-seeking individuals from seven study sites (N = 276). We estimated the risk using three state-of-the-art assessment instruments (BPSS-P, BARS, EPIbipolar).

RESULTS

For BPSS-P, SVM achieved a fair performance of Cohen's κ of 0.235 (95% CI 0.11-0.361) and a balanced accuracy of 63.1% (95% CI 55.9-70.3) in the 10-fold cross-validation. In the leave-one-site-out cross-validation, the model performed with a Cohen's κ of 0.128 (95% CI -0.069 to 0.325) and a balanced accuracy of 56.2% (95% CI 44.6-67.8). BARS and EPIbipolar could not be predicted. In post hoc analyses, regional surface area, subcortical volumes as well as hyperparameter optimization did not improve the performance.

CONCLUSIONS

Individuals at risk for bipolar disorder, as assessed by BPSS-P, display brain structural alterations that can be detected using machine learning. The achieved performance is comparable to previous studies which attempted to classify patients with manifest disease and healthy controls. Unlike previous studies of bipolar risk, our multicenter design permitted a leave-one-site-out cross-validation. Whole-brain cortical thickness seems to be superior to other structural brain features.

Intrusive Traumatic Re-Experiencing Domain: Functional Connectivity Feature Classification by the ENIGMA PTSD Consortium

Background

Intrusive traumatic re-experiencing domain (ITRED) was recently introduced as a novel perspective on posttraumatic psychopathology, proposing to focus research of posttraumatic stress disorder (PTSD) on the unique symptoms of intrusive and involuntary re-experiencing of the trauma, namely, intrusive memories, nightmares, and flashbacks. The aim of the present study was to explore ITRED from a neural network connectivity perspective.

Methods

Data were collected from 9 sites taking part in the ENIGMA (Enhancing Neuro Imaging Genetics through Meta Analysis) PTSD Consortium (n= 584) and included itemized PTSD symptom scores and resting-state functional connectivity (rsFC) data. We assessed the utility of rsFC in classifying PTSD, ITRED-only (no PTSD diagnosis), and trauma-exposed (TE)-only (no PTSD or ITRED) groups using a machine learning approach, examining well-known networks implicated in PTSD. A random forest classification model was built on a training set using cross-validation, and the averaged cross-validation model performance for classification was evaluated using the area under the curve. The model was tested using a fully independent portion of the data (test dataset), and the test area under the curve was evaluated.

Results

rsFC signatures differentiated TE-only participants from PTSD and ITRED-only participants at about 60% accuracy. Conversely, rsFC signatures did not differentiate PTSD from ITRED-only individuals (45% accuracy). Common features differentiating TE-only participants from PTSD and ITRED-only participants mainly involved default mode network-related pathways. Some unique features, such as connectivity within the frontoparietal network, differentiated TE-only participants from one group (PTSD or ITRED-only) but to a lesser extent from the other group.

Conclusions

Neural network connectivity supports ITRED as a novel neurobiologically based approach to classifying posttrauma psychopathology.

Multi-feature concatenation and multi-classifier stacking: An interpretable and generalizable machine learning method for MDD discrimination with rsfMRI

Major depressive disorder (MDD) is a serious and heterogeneous psychiatric disorder that needs accurate diagnosis. Resting-state functional MRI (rsfMRI), which captures multiple perspectives on brain structure, function, and connectivity, is increasingly applied in the diagnosis and pathological research of MDD. Different machine learning algorithms are then developed to exploit the rich information in rsfMRI and discriminate MDD patients from normal controls. Despite recent advances reported, the MDD discrimination accuracy has room for further improvement. The generalizability and interpretability of the discrimination method are not sufficiently addressed either. Here, we propose a machine learning method (MFMC) for MDD discrimination by concatenating multiple features and stacking multiple classifiers. MFMC is tested on the REST-meta-MDD data set that contains 2428 subjects collected from 25 different sites. MFMC yields 96.9% MDD discrimination accuracy, demonstrating a significant improvement over existing methods. In addition, the generalizability of MFMC is validated by the good performance when the training and testing subjects are from independent sites. The use of XGBoost as the meta classifier allows us to probe the decision process of MFMC. We identify 13 feature values related to 9 brain regions including the posterior cingulate gyrus, superior frontal gyrus orbital part, and angular gyrus, which contribute most to the classification and also demonstrate significant differences at the group level. The use of these 13 feature values alone can reach 87% of MFMC's full performance when taking all feature values. These features may serve as clinically useful diagnostic and prognostic biomarkers for MDD in the future.

Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium

BACKGROUND

Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group.

METHODS

We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality.

RESULTS

We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance.

CONCLUSION

These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

The functional connectome in obsessive-compulsive disorder: resting-state mega-analysis and machine learning classification for the ENIGMA-OCD consortium

Current knowledge about functional connectivity in obsessive-compulsive disorder (OCD) is based on small-scale studies, limiting the generalizability of results. Moreover, the majority of studies have focused only on predefined regions or functional networks rather than connectivity throughout the entire brain. Here, we investigated differences in resting-state functional connectivity between OCD patients and healthy controls (HC) using mega-analysis of data from 1024 OCD patients and 1028 HC from 28 independent samples of the ENIGMA-OCD consortium. We assessed group differences in whole-brain functional connectivity at both the regional and network level, and investigated whether functional connectivity could serve as biomarker to identify patient status at the individual level using machine learning analysis. The mega-analyses revealed widespread abnormalities in functional connectivity in OCD, with global hypo-connectivity (Cohen's d: -0.27 to -0.13) and few hyper-connections, mainly with the thalamus (Cohen's d: 0.19 to 0.22). Most hypo-connections were located within the sensorimotor network and no fronto-striatal abnormalities were found. Overall, classification performances were poor, with area-under-the-receiver-operating-characteristic curve (AUC) scores ranging between 0.567 and 0.673, with better classification for medicated (AUC = 0.702) than unmedicated (AUC = 0.608) patients versus healthy controls. These findings provide partial support for existing pathophysiological models of OCD and highlight the important role of the sensorimotor network in OCD. However, resting-state connectivity does not so far provide an accurate biomarker for identifying patients at the individual level.

The association between cortical gyrification and sleep in adolescents and young adults

Study objectives

Healthy sleep is important for adolescent neurodevelopment, and relationships between brain structure and sleep can vary in strength over this maturational window. Although cortical gyrification is increasingly considered a useful index for understanding cognitive and emotional outcomes in adolescence, and sleep is also a strong predictor of such outcomes, we know relatively little about associations between cortical gyrification and sleep.

Methods

Using Local gyrification index (lGI) of 34 bilateral brain regions and regularized regression for feature selection, we examined gyrification-sleep relationships in the Neuroimaging and Pediatric Sleep databank (252 participants; 9-26 years; 58.3% female) and identified developmentally invariant (stable across age) or developmentally specific (observed only during discrete age intervals) brain-sleep associations. Naturalistic sleep characteristics (duration, timing, continuity, and regularity) were estimated from wrist actigraphy.

Results

For most brain regions, greater lGI was associated with longer sleep duration, earlier sleep timing, lower variability in sleep regularity, and shorter time awake after sleep onset. lGI in frontoparietal network regions showed associations with sleep patterns that were stable across age. However, in default mode network regions, lGI was only associated with sleep patterns from late childhood through early-to-mid adolescence, a period of vulnerability for mental health disorders.

Conclusions

We detected both developmentally invariant and developmentally specific ties between local gyrification and naturalistic sleep patterns. Default mode network regions may be particularly susceptible to interventions promoting more optimal sleep during childhood and adolescence.

Challenges of implementing computer-aided diagnostic models for neuroimages in a clinical setting

Advances in artificial intelligence have cultivated a strong interest in developing and validating the clinical utilities of computer-aided diagnostic models. Machine learning for diagnostic neuroimaging has often been applied to detect psychological and neurological disorders, typically on small-scale datasets or data collected in a research setting. With the collection and collation of an ever-growing number of public datasets that researchers can freely access, much work has been done in adapting machine learning models to classify these neuroimages by diseases such as Alzheimer's, ADHD, autism, bipolar disorder, and so on. These studies often come with the promise of being implemented clinically, but despite intense interest in this topic in the laboratory, limited progress has been made in clinical implementation. In this review, we analyze challenges specific to the clinical implementation of diagnostic AI models for neuroimaging data, looking at the differences between laboratory and clinical settings, the inherent limitations of diagnostic AI, and the different incentives and skill sets between research institutions, technology companies, and hospitals. These complexities need to be recognized in the translation of diagnostic AI for neuroimaging from the laboratory to the clinic.

Classifying youth with bipolar disorder versus healthy youth using cerebral blood flow patterns

BACKGROUND

Clinical neuroimaging studies often investigate group differences between patients and controls, yet multivariate imaging features may enable individual-level classification. This study aims to classify youth with bipolar disorder (BD) versus healthy youth using grey matter cerebral blood flow (CBF) data analyzed with logistic regressions.

METHODS

Using a 3 Tesla magnetic resonance imaging (MRI) system, we collected pseudo-continuous, arterial spin-labelling, resting-state functional MRI (rfMRI) and T 1-weighted images from youth with BD and healthy controls. We used 3 logistic regression models to classify youth with BD versus controls, controlling for age and sex, using mean grey matter CBF as a single explanatory variable, quantitative CBF features based on principal component analysis (PCA) or relative (intensity-normalized) CBF features based on PCA. We also carried out a comparison analysis using rfMRI data.

RESULTS

The study included 46 patients with BD (mean age 17 yr, standard deviation [SD] 1 yr; 25 females) and 49 healthy controls (mean age 16 yr, SD 2 yr; 24 females). Global mean CBF and multivariate quantitative CBF offered similar classification performance that was above chance. The association between CBF images and the feature map was not significantly different between groups (p = 0.13); however, the multivariate classifier identified regions with lower CBF among patients with BD (ΔCBF = -2.94 mL/100 g/min; permutation test p = 0047). Classification performance decreased when considering rfMRI data.

LIMITATIONS

We cannot comment on which CBF principal component is most relevant to the classification. Participants may have had various mood states, comorbidities, demographics and medication records.

CONCLUSION

Brain CBF features can classify youth with BD versus healthy controls with above-chance accuracy using logistic regression. A global CBF feature may offer similar classification performance to distinct multivariate CBF features.

Evaluation of boundaries between mood and psychosis disorder using dynamic functional network connectivity (dFNC) via deep learning classification

The validity and reliability of diagnoses in psychiatry is a challenging topic in mental health. The current mental health categorization is based primarily on symptoms and clinical course and is not biologically validated. Among multiple ongoing efforts, neurological observations alongside clinical evaluations are considered to be potential solutions to address diagnostic problems. The Bipolar-Schizophrenia Network on Intermediate Phenotypes (B-SNIP) has published multiple papers attempting to reclassify psychotic illnesses based on biological rather than symptomatic measures. However, the effort to investigate the relationship between this new categorization approach and other neuroimaging techniques, including resting-state fMRI data, is still limited. This study focused on investigating the relationship between different psychotic disorders categorization methods and resting-state fMRI-based measures called dynamic functional network connectivity (dFNC) using state-of-the-art artificial intelligence (AI) approaches. We applied our method to 613 subjects, including individuals with psychosis and healthy controls, which were classified using both the Diagnostic and Statistical Manual of Mental Disorders (DSM-IV) and the B-SNIP biomarker-based (Biotype) approach. Statistical group differences and cross-validated classifiers were performed within each framework to assess how different categories. Results highlight interesting differences in occupancy in both DSM-IV and Biotype categorizations compared to healthy individuals, which are distributed across specific transient connectivity states. Biotypes tended to show less distinctiveness in occupancy level and included fewer cellwise differences. Classification accuracy obtained by DSM-IV and Biotype categories were both well above chance. Results provided new insights and highlighted the benefits of both DSM-IV and biology-based categories while also emphasizing the importance of future work in this direction, including employing further data types.

Machine Learning Prediction of Estimated Risk for Bipolar Disorders Using Hippocampal Subfield and Amygdala Nuclei Volumes

The pathophysiology of bipolar disorder (BD) remains mostly unclear. Yet, a valid biomarker is necessary to improve upon the early detection of this serious disorder. Patients with manifest BD display reduced volumes of the hippocampal subfields and amygdala nuclei. In this pre-registered analysis, we used structural MRI (n = 271, 7 sites) to compare volumes of hippocampus, amygdala and their subfields/nuclei between help-seeking subjects divided into risk groups for BD as estimated by BPSS-P, BARS and EPIbipolar. We performed between-group comparisons using linear mixed effects models for all three risk assessment tools. Additionally, we aimed to differentiate the risk groups using a linear support vector machine. We found no significant volume differences between the risk groups for all limbic structures during the main analysis. However, the SVM could still classify subjects at risk according to BPSS-P criteria with a balanced accuracy of 66.90% (95% CI 59.2-74.6) for 10-fold cross-validation and 61.9% (95% CI 52.0-71.9) for leave-one-site-out. Structural alterations of the hippocampus and amygdala may not be as pronounced in young people at risk; nonetheless, machine learning can predict the estimated risk for BD above chance. This suggests that neural changes may not merely be a consequence of BD and may have prognostic clinical value.

PREDICTING DEPRESSION RISK IN EARLY ADOLESCENCE VIA MULTIMODAL BRAIN IMAGING

Depression is an incapacitating psychiatric disorder with high prevalence in adolescent populations that is influenced by many risk factors, including family history of depression. The ability to predict who may develop depression before adolescence, when rates of depression increase markedly, is important for early intervention and prevention. Using a large longitudinal sample from the Adolescent Brain Cognitive Development (ABCD) Study (2658 participants after imaging quality control, between 9-10 years at baseline), we applied machine learning methods on a set of comprehensive multimodal neuroimaging features to predict depression risk at the two-year follow-up from the baseline visit. Features include derivatives from structural MRI, diffusion tensor imaging, and task and rest functional MRI. A rigorous cross-validation method of leave-one-site-out was used. Additionally, we tested the prediction models in a high-risk group of participants with parental history of depression (N=625). The results showed all brain features had prediction scores significantly better than expected by chance. When predicting depression onset in the high-risk group, brain features from resting-state functional connectomes showed the best classification performance, outperforming other brain features based on structural MRI and task-based fMRI. Results demonstrate that the functional connectivity of the brain can predict the risk of depression in early adolescence better than other univariate neuroimaging derivatives, highlighting the key role of the interacting elements of the connectome capturing more individual variability in psychopathology compared to measures of single brain regions.

Diagnosis and management of bipolar disorders

Bipolar disorders (BDs) are recurrent and sometimes chronic disorders of mood that affect around 2% of the world's population and encompass a spectrum between severe elevated and excitable mood states (mania) to the dysphoria, low energy, and despondency of depressive episodes. The illness commonly starts in young adults and is a leading cause of disability and premature mortality. The clinical manifestations of bipolar disorder can be markedly varied between and within individuals across their lifespan. Early diagnosis is challenging and misdiagnoses are frequent, potentially resulting in missed early intervention and increasing the risk of iatrogenic harm. Over 15 approved treatments exist for the various phases of bipolar disorder, but outcomes are often suboptimal owing to insufficient efficacy, side effects, or lack of availability. Lithium, the first approved treatment for bipolar disorder, continues to be the most effective drug overall, although full remission is only seen in a subset of patients. Newer atypical antipsychotics are increasingly being found to be effective in the treatment of bipolar depression; however, their long term tolerability and safety are uncertain. For many with bipolar disorder, combination therapy and adjunctive psychotherapy might be necessary to treat symptoms across different phases of illness. Several classes of medications exist for treating bipolar disorder but predicting which medication is likely to be most effective or tolerable is not yet possible. As pathophysiological insights into the causes of bipolar disorders are revealed, a new era of targeted treatments aimed at causal mechanisms, be they pharmacological or psychosocial, will hopefully be developed. For the time being, however, clinical judgment, shared decision making, and empirical follow-up remain essential elements of clinical care. This review provides an overview of the clinical features, diagnostic subtypes, and major treatment modalities available to treat people with bipolar disorder, highlighting recent advances and ongoing therapeutic challenges.

An Overview of Bipolar Disorder Diagnosis Using Machine Learning Approaches: Clinical Opportunities and Challenges

Objective: Automatic diagnosis of psychiatric disorders such as bipolar disorder (BD) through machine learning techniques has attracted substantial attention from psychiatric and artificial intelligence communities. These approaches mostly rely on various biomarkers extracted from electroencephalogram (EEG) or magnetic resonance imaging (MRI)/functional MRI (fMRI) data. In this paper, we provide an updated overview of existing machine learning-based methods for bipolar disorder (BD) diagnosis using MRI and EEG data. Method : This study is a short non-systematic review with the aim of describing the current situation in automatic diagnosis of BD using machine learning methods. Therefore, an appropriate literature search was conducted via relevant keywords for original EEG/MRI studies on distinguishing BD from other conditions, particularly from healthy peers, in PubMed, Web of Science, and Google Scholar databases. Results: We reviewed 26 studies, including 10 EEG studies and 16 MRI studies (including structural and functional MRI), that used traditional machine learning methods and deep learning algorithms to automatically detect BD. The reported accuracies for EEG studies is about 90%, while the reported accuracies for MRI studies remains below the minimum level for clinical relevance, i.e. about 80% of the classification outcome for traditional machine learning methods. However, deep learning techniques have generally achieved accuracies higher than 95%. Conclusion: Research utilizing machine learning applied to EEG signals and brain images has provided proof of concept for how this innovative technique can help psychiatrists distinguish BD patients from healthy people. However, the results have been somewhat contradictory and we must keep away from excessive optimistic interpretations of the findings. Much progress is still needed to reach the level of clinical practice in this field.

Mega-analysis of association between obesity and cortical morphology in bipolar disorders: ENIGMA study in 2832 participants

BACKGROUND

Obesity is highly prevalent and disabling, especially in individuals with severe mental illness including bipolar disorders (BD). The brain is a target organ for both obesity and BD. Yet, we do not understand how cortical brain alterations in BD and obesity interact.

METHODS

We obtained body mass index (BMI) and MRI-derived regional cortical thickness, surface area from 1231 BD and 1601 control individuals from 13 countries within the ENIGMA-BD Working Group. We jointly modeled the statistical effects of BD and BMI on brain structure using mixed effects and tested for interaction and mediation. We also investigated the impact of medications on the BMI-related associations.

RESULTS

BMI and BD additively impacted the structure of many of the same brain regions. Both BMI and BD were negatively associated with cortical thickness, but not surface area. In most regions the number of jointly used psychiatric medication classes remained associated with lower cortical thickness when controlling for BMI. In a single region, fusiform gyrus, about a third of the negative association between number of jointly used psychiatric medications and cortical thickness was mediated by association between the number of medications and higher BMI.

CONCLUSIONS

We confirmed consistent associations between higher BMI and lower cortical thickness, but not surface area, across the cerebral mantle, in regions which were also associated with BD. Higher BMI in people with BD indicated more pronounced brain alterations. BMI is important for understanding the neuroanatomical changes in BD and the effects of psychiatric medications on the brain.

Genetic associations between bipolar disorder and brain structural phenotypes

Patients with bipolar disorder (BD) and their first-degree relatives exhibit alterations in brain volume and cortical structure, whereas the underlying genetic mechanisms remain unclear. In this study, based on the published genome-wide association studies (GWAS), the extent of polygenic overlap between BD and 15 brain structural phenotypes was investigated using linkage disequilibrium score regression and MiXeR tool, and the shared genomic loci were discovered by conjunctional false discovery rate (conjFDR) and expression quantitative trait loci (eQTL) analyses. MiXeR estimated the overall measure of polygenic overlap between BD and brain structural phenotypes as 4-53% on a 0-100% scale (as quantified by the Dice coefficient). Subsequent conjFDR analyses identified 54 independent loci (71 risk single-nucleotide polymorphisms) jointly associated with BD and brain structural phenotypes with a conjFDR < 0.05, among which 33 were novel that had not been reported in the previous BD GWAS. Follow-up eQTL analyses in respective brain regions both confirmed well-known risk genes (e.g. CACNA1C, NEK4, GNL3, MAPK3) and discovered novel risk genes (e.g. LIMK2 and CAMK2N2). This study indicates a substantial shared genetic basis between BD and brain structural phenotypes, and provides novel insights into the developmental origin of BD and related biological mechanisms.

Shared and Specific Patterns of Structural Brain Connectivity Across Affective and Psychotic Disorders

BACKGROUND

Altered brain structural connectivity has been implicated in the pathophysiology of psychiatric disorders including schizophrenia (SZ), bipolar disorder (BD), and major depressive disorder (MDD). However, it is unknown which part of these connectivity abnormalities are disorder specific and which are shared across the spectrum of psychotic and affective disorders. We investigated common and distinct brain connectivity alterations in a large sample (N = 1743) of patients with SZ, BD, or MDD and healthy control (HC) subjects.

METHODS

This study examined diffusion-weighted imaging-based structural connectome topology in 720 patients with MDD, 112 patients with BD, 69 patients with SZ, and 842 HC subjects (mean age of all subjects: 35.7 years). Graph theory-based network analysis was used to investigate connectome organization. Machine learning algorithms were trained to classify groups based on their structural connectivity matrices.

RESULTS

Groups differed significantly in the network metrics global efficiency, clustering, present edges, and global connectivity strength with a converging pattern of alterations between diagnoses (e.g., efficiency: HC > MDD > BD > SZ, false discovery rate-corrected p = .028). Subnetwork analysis revealed a common core of edges that were affected across all 3 disorders, but also revealed differences between disorders. Machine learning algorithms could not discriminate between disorders but could discriminate each diagnosis from HC. Furthermore, dysconnectivity patterns were found most pronounced in patients with an early disease onset irrespective of diagnosis.

CONCLUSIONS

We found shared and specific signatures of structural white matter dysconnectivity in SZ, BD, and MDD, leading to commonly reduced network efficiency. These results showed a compromised brain communication across a spectrum of major psychiatric disorders.

Precision neuroimaging biomarkers for bipolar disorder

Bipolar disorder (BD) is a severe mental illness associated with alterations in brain organization. Neuroimaging studies have generated a large body of knowledge regarding brain morphological and functional abnormalities in BD. Current advances in the field have focussed on the need for more precise neuroimaging biomarkers. Here we present a selective overview of precision neuroimaging biomarkers for BD, focussing on personalized metrics and novel neuroimaging methods aiming to provide mechanistic insights into the brain alterations associated with BD. The evidence presented covers (a) machine learning techniques applied to neuroimaging data to differentiate patients with BD from healthy individuals or other clinical groups; (b) the 'brain-age-gap-estimation (brainAGE), which is an individualized measure of brain health; (c) diffusional kurtosis imaging (DKI), neurite orientation dispersion and density imaging (NODDI) and Positron Emission Tomography (PET) techniques that open new opportunities to measure microstructural changes in neurite/synaptic integrity and function.

Accelerated functional brain aging in major depressive disorder: evidence from a large scale fMRI analysis of Chinese participants

Major depressive disorder (MDD) is one of the most common mental health conditions that has been intensively investigated for its association with brain atrophy and mortality. Recent studies suggest that the deviation between the predicted and the chronological age can be a marker of accelerated brain aging to characterize MDD. However, current conclusions are usually drawn based on structural MRI information collected from Caucasian participants. The universality of this biomarker needs to be further validated by subjects with different ethnic/racial backgrounds and by different types of data. Here we make use of the REST-meta-MDD, a large scale resting-state fMRI dataset collected from multiple cohort participants in China. We develop a stacking machine learning model based on 1101 healthy controls, which estimates a subject's chronological age from fMRI with promising accuracy. The trained model is then applied to 1276 MDD patients from 24 sites. We observe that MDD patients exhibit a +4.43 years (p < 0.0001, Cohen's d = 0.31, 95% CI: 2.23-3.88) higher brain-predicted age difference (brain-PAD) compared to controls. In the MDD subgroup, we observe a statistically significant +2.09 years (p < 0.05, Cohen's d = 0.134525) brain-PAD in antidepressant users compared to medication-free patients. The statistical relationship observed is further checked by three different machine learning algorithms. The positive brain-PAD observed in participants in China confirms the presence of accelerated brain aging in MDD patients. The utilization of functional brain connectivity for age estimation verifies existing findings from a new dimension.

Statistical quantification of confounding bias in machine learning models

BACKGROUND

The lack of nonparametric statistical tests for confounding bias significantly hampers the development of robust, valid, and generalizable predictive models in many fields of research. Here I propose the partial confounder test, which, for a given confounder variable, probes the null hypotheses of the model being unconfounded.

RESULTS

The test provides a strict control for type I errors and high statistical power, even for nonnormally and nonlinearly dependent predictions, often seen in machine learning. Applying the proposed test on models trained on large-scale functional brain connectivity data (N= 1,865) (i) reveals previously unreported confounders and (ii) shows that state-of-the-art confound mitigation approaches may fail preventing confounder bias in several cases.

CONCLUSIONS

The proposed test (implemented in the package mlconfound; https://mlconfound.readthedocs.io) can aid the assessment and improvement of the generalizability and validity of predictive models and, thereby, fosters the development of clinically useful machine learning biomarkers.

Machine learning algorithm performance evaluation in structural magnetic resonance imaging-based classification of pediatric bipolar disorders type I patients

The diagnosis based on clinical assessment of pediatric bipolar disorder (PBD) may sometimes lead to misdiagnosis in clinical practice. For the past several years, machine learning (ML) methods were introduced for the classification of bipolar disorder (BD), which were helpful in the diagnosis of BD. In this study, brain cortical thickness and subcortical volume of 33 PBD-I patients and 19 age-sex matched healthy controls (HCs) were extracted from the magnetic resonance imaging (MRI) data and set as features for classification. The dimensionality reduced feature subset, which was filtered by Lasso or f_classif, was sent to the six classifiers (logistic regression (LR), support vector machine (SVM), random forest classifier, naïve Bayes, k-nearest neighbor, and AdaBoost algorithm), and the classifiers were trained and tested. Among all the classifiers, the top two classifiers with the highest accuracy were LR (84.19%) and SVM (82.80%). Feature selection was performed in the six algorithms to obtain the most important variables including the right middle temporal gyrus and bilateral pallidum, which is consistent with structural and functional anomalous changes in these brain regions in PBD patients. These findings take the computer-aided diagnosis of BD a step forward.

Morphometric Integrated Classification Index: A Multisite Model-Based, Interpretable, Shareable and Evolvable Biomarker for Schizophrenia

BACKGROUND AND HYPOTHESIS

Multisite massive schizophrenia neuroimaging data sharing is becoming critical in understanding the pathophysiological mechanism and making an objective diagnosis of schizophrenia; it remains challenging to obtain a generalizable and interpretable, shareable, and evolvable neuroimaging biomarker for schizophrenia diagnosis.

STUDY DESIGN

A Morphometric Integrated Classification Index (MICI) was proposed as a potential biomarker for schizophrenia diagnosis based on structural magnetic resonance imaging data of 1270 subjects from 10 sites (588 schizophrenia patients and 682 normal controls). An optimal XGBoost classifier plus sample-weighted SHapley Additive explanation algorithms were used to construct the MICI measure.

STUDY RESULTS

The MICI measure achieved comparable performance with the sample-weighted ensembling model and merged model based on raw data (Delong test, P > 0.82) while outperformed the single-site models (Delong test, P < 0.05) in either the independent-sample testing datasets from the 9 sites or the independent-site dataset (generalizable). Besides, when new sites were embedded in, the performance of this measure was gradually increasing (evolvable). Finally, MICI was strongly associated with the severity of schizophrenia brain structural abnormality, with the patients' positive and negative symptoms, and with the brain expression profiles of schizophrenia risk genes (interpretable).

CONCLUSIONS

In summary, the proposed MICI biomarker may provide a simple and explainable way to support clinicians for objectively diagnosing schizophrenia. Finally, we developed an online model share platform to promote biomarker generalization and provide free individual prediction services (http://micc.tmu.edu.cn/mici/index.html).

Diagnosis of bipolar disorders and body mass index predict clustering based on similarities in cortical thickness-ENIGMA study in 2436 individuals

AIMS

Rates of obesity have reached epidemic proportions, especially among people with psychiatric disorders. While the effects of obesity on the brain are of major interest in medicine, they remain markedly under-researched in psychiatry.

METHODS

We obtained body mass index (BMI) and magnetic resonance imaging-derived regional cortical thickness, surface area from 836 bipolar disorders (BD) and 1600 control individuals from 14 sites within the ENIGMA-BD Working Group. We identified regionally specific profiles of cortical thickness using K-means clustering and studied clinical characteristics associated with individual cortical profiles.

RESULTS

We detected two clusters based on similarities among participants in cortical thickness. The lower thickness cluster (46.8% of the sample) showed thinner cortex, especially in the frontal and temporal lobes and was associated with diagnosis of BD, higher BMI, and older age. BD individuals in the low thickness cluster were more likely to have the diagnosis of bipolar disorder I and less likely to be treated with lithium. In contrast, clustering based on similarities in the cortical surface area was unrelated to BD or BMI and only tracked age and sex.

CONCLUSIONS

We provide evidence that both BD and obesity are associated with similar alterations in cortical thickness, but not surface area. The fact that obesity increased the chance of having low cortical thickness could explain differences in cortical measures among people with BD. The thinner cortex in individuals with higher BMI, which was additive and similar to the BD-associated alterations, may suggest that treating obesity could lower the extent of cortical thinning in BD.

Training a machine learning classifier to identify ADHD based on real-world clinical data from medical records

The diagnostic process of attention deficit hyperactivity disorder (ADHD) is complex and relies on criteria sensitive to subjective biases. This may cause significant delays in appropriate treatment initiation. An automated analysis relying on subjective and objective measures might not only simplify the diagnostic process and reduce the time to diagnosis, but also improve reproducibility. While recent machine learning studies have succeeded at distinguishing ADHD from healthy controls, the clinical process requires differentiating among other or multiple psychiatric conditions. We trained a linear support vector machine (SVM) classifier to detect participants with ADHD in a population showing a broad spectrum of psychiatric conditions using anonymized data from clinical records (N = 299 participants). We differentiated children and adolescents with ADHD from those not having the condition with an accuracy of 66.1%. SVM using single features showed slight differences between features and overlapping standard deviations of the achieved accuracies. An automated feature selection achieved the best performance using a combination 19 features. Real-world clinical data from medical records can be used to automatically identify individuals with ADHD among help-seeking individuals using machine learning. The relevant diagnostic information can be reduced using an automated feature selection without loss of performance. A broad combination of symptoms across different domains, rather than specific domains, seems to indicate an ADHD diagnosis.

Comparing the Effectiveness of Brain Structural Imaging, Resting-state fMRI, and Naturalistic fMRI in Recognizing Social Anxiety Disorder in Children and Adolescents

Social anxiety disorder (SAD) is a common anxiety disorder in childhood and adolescence. Studies on SAD in adults have reported both structural and functional aberrancies of the brain at the group level. However, evidence has shown differences in anxiety-related brain abnormalities between adolescents and adults. Since children and adolescents can afford limited scan time, optimizing the scan tasks is essential for SAD research in children and adolescents. Thus, we need to address whether brain structure, resting-state fMRI, and naturalistic imaging enable individualized identification of SAD in children and adolescents, which measurement is more effective, and whether pooling multi-modal features can improve the identification of SAD. We comprehensively addressed these questions by building machine learning models based on parcel-wise brain features. We found that naturalistic fMRI yielded higher classification accuracy (69.17%) than the other modalities and the classification performance showed dependence on the contents of the movie. The classification models also identified contributing brain regions, some of which exhibited correlations with the symptoms scores of SAD. However, pooling brain features from the three modalities did not help enhance the classification accuracy. These results support the application of carefully designed naturalistic imaging in recognizing children and adolescents at risk of SAD.

Phenotypes, mechanisms and therapeutics: insights from bipolar disorder GWAS findings

Genome-wide association studies (GWAS) have reported substantial genomic loci significantly associated with clinical risk of bipolar disorder (BD), and studies combining techniques of genetics, neuroscience, neuroimaging, and pharmacology are believed to help tackle clinical problems (e.g., identifying novel therapeutic targets). However, translating findings of psychiatric genetics into biological mechanisms underlying BD pathogenesis remains less successful. Biological impacts of majority of BD GWAS risk loci are obscure, and the involvement of many GWAS risk genes in this illness is yet to be investigated. It is thus necessary to review the progress of applying BD GWAS risk genes in the research and intervention of the disorder. A comprehensive literature search found that a number of such risk genes had been investigated in cellular or animal models, even before they were highlighted in BD GWAS. Intriguingly, manipulation of many BD risk genes (e.g., ANK3, CACNA1C, CACNA1B, HOMER1, KCNB1, MCHR1, NCAN, SHANK2 etc.) resulted in altered murine behaviors largely restoring BD clinical manifestations, including mania-like symptoms such as hyperactivity, anxiolytic-like behavior, as well as antidepressant-like behavior, and these abnormalities could be attenuated by mood stabilizers. In addition to recapitulating phenotypic characteristics of BD, some GWAS risk genes further provided clues for the neurobiology of this illness, such as aberrant activation and functional connectivity of brain areas in the limbic system, and modulated dendritic spine morphogenesis as well as synaptic plasticity and transmission. Therefore, BD GWAS risk genes are undoubtedly pivotal resources for modeling this illness, and might be translational therapeutic targets in the future clinical management of BD. We discuss both promising prospects and cautions in utilizing the bulk of useful resources generated by GWAS studies. Systematic integrations of findings from genetic and neuroscience studies are called for to promote our understanding and intervention of BD.

Multi-centre classification of functional neurological disorders based on resting-state functional connectivity

•

Using machine learning on multi-centre data, FND patients were successfully classified with an accuracy of 72%.

•

The angular- and supramarginal gyri, cingular- and insular cortex, and the hippocampus were the most discriminant regions.

•

To provide diagnostic utility, future studies must include patients with similar symptoms but different diagnoses.

Background

Patients suffering from functional neurological disorder (FND) experience disabling neurological symptoms not caused by an underlying classical neurological disease (such as stroke or multiple sclerosis). The diagnosis is made based on reliable positive clinical signs, but clinicians often require additional time- and cost consuming medical tests and examinations. Resting-state functional connectivity (RS FC) showed its potential as an imaging-based adjunctive biomarker to help distinguish patients from healthy controls and could represent a “rule-in” procedure to assist in the diagnostic process. However, the use of RS FC depends on its applicability in a multi-centre setting, which is particularly susceptible to inter-scanner variability. The aim of this study was to test the robustness of a classification approach based on RS FC in a multi-centre setting.

Methods

This study aimed to distinguish 86 FND patients from 86 healthy controls acquired in four different centres using a multivariate machine learning approach based on whole-brain resting-state functional connectivity. First, previously published results were replicated in each centre individually (intra-centre cross-validation) and its robustness across inter-scanner variability was assessed by pooling all the data (pooled cross-validation). Second, we evaluated the generalizability of the method by using data from each centre once as a test set, and the data from the remaining centres as a training set (inter-centre cross-validation).

Results

FND patients were successfully distinguished from healthy controls in the replication step (accuracy of 74%) as well as in each individual additional centre (accuracies of 73%, 71% and 70%). The pooled cross validation confirmed that the classifier was robust with an accuracy of 72%. The results survived post-hoc adjustment for anxiety, depression, psychotropic medication intake, and symptom severity. The most discriminant features involved the angular- and supramarginal gyri, sensorimotor cortex, cingular- and insular cortex, and hippocampal regions. The inter-centre validation step did not exceed chance level (accuracy below 50%).

Conclusions

The results demonstrate the applicability of RS FC to correctly distinguish FND patients from healthy controls in different centres and its robustness against inter-scanner variability. In order to generalize its use across different centres and aim for clinical application, future studies should work towards optimization of acquisition parameters and include neurological and psychiatric control groups presenting with similar symptoms.

Machine learning generalizability across healthcare settings: insights from multi-site COVID-19 screening

As patient health information is highly regulated due to privacy concerns, most machine learning (ML)-based healthcare studies are unable to test on external patient cohorts, resulting in a gap between locally reported model performance and cross-site generalizability. Different approaches have been introduced for developing models across multiple clinical sites, however less attention has been given to adopting ready-made models in new settings. We introduce three methods to do this-(1) applying a ready-made model "as-is" (2); readjusting the decision threshold on the model's output using site-specific data and (3); finetuning the model using site-specific data via transfer learning. Using a case study of COVID-19 diagnosis across four NHS Hospital Trusts, we show that all methods achieve clinically-effective performances (NPV > 0.959), with transfer learning achieving the best results (mean AUROCs between 0.870 and 0.925). Our models demonstrate that site-specific customization improves predictive performance when compared to other ready-made approaches.

Cross disorder comparisons of brain structure in schizophrenia, bipolar disorder, major depressive disorder, and 22q11.2 deletion syndrome: A review of ENIGMA findings

This review compares the main brain abnormalities in schizophrenia (SZ), bipolar disorder (BD), major depressive disorder (MDD), and 22q11.2 Deletion Syndrome (22q11DS) determined by ENIGMA (Enhancing Neuro Imaging Genetics through Meta Analysis) consortium investigations. We obtained ranked effect sizes for subcortical volumes, regional cortical thickness, cortical surface area, and diffusion tensor imaging abnormalities, comparing each of these disorders relative to healthy controls. In addition, the studies report on significant associations between brain imaging metrics and disorder-related factors such as symptom severity and treatments. Visual comparison of effect size profiles shows that effect sizes are generally in the same direction and scale in severity with the disorders (in the order SZ > BD > MDD). The effect sizes for 22q11DS, a rare genetic syndrome that increases the risk for psychiatric disorders, appear to be much larger than for either of the complex psychiatric disorders. This is consistent with the idea of generally larger effects on the brain of rare compared to common genetic variants. Cortical thickness and surface area effect sizes for 22q11DS with psychosis compared to 22q11DS without psychosis are more similar to those of SZ and BD than those of MDD; a pattern not observed for subcortical brain structures and fractional anisotropy effect sizes. The observed similarities in effect size profiles for cortical measures across the psychiatric disorders mimic those observed for shared genetic variance between these disorders reported based on family and genetic studies and are consistent with shared genetic risk for SZ and BD and structural brain phenotypes.

Application of a Machine Learning Algorithm for Structural Brain Images in Chronic Schizophrenia to Earlier Clinical Stages of Psychosis and Autism Spectrum Disorder: A Multiprotocol Imaging Dataset Study

BACKGROUND AND HYPOTHESIS

Machine learning approaches using structural magnetic resonance imaging (MRI) can be informative for disease classification; however, their applicability to earlier clinical stages of psychosis and other disease spectra is unknown. We evaluated whether a model differentiating patients with chronic schizophrenia (ChSZ) from healthy controls (HCs) could be applied to earlier clinical stages such as first-episode psychosis (FEP), ultra-high risk for psychosis (UHR), and autism spectrum disorders (ASDs).

STUDY DESIGN

Total 359 T1-weighted MRI scans, including 154 individuals with schizophrenia spectrum (UHR, n = 37; FEP, n = 24; and ChSZ, n = 93), 64 with ASD, and 141 HCs, were obtained using three acquisition protocols. Of these, data regarding ChSZ (n = 75) and HC (n = 101) from two protocols were used to build a classifier (training dataset). The remainder was used to evaluate the classifier (test, independent confirmatory, and independent group datasets). Scanner and protocol effects were diminished using ComBat.

STUDY RESULTS

The accuracy of the classifier for the test and independent confirmatory datasets were 75% and 76%, respectively. The bilateral pallidum and inferior frontal gyrus pars triangularis strongly contributed to classifying ChSZ. Schizophrenia spectrum individuals were more likely to be classified as ChSZ compared to ASD (classification rate to ChSZ: UHR, 41%; FEP, 54%; ChSZ, 70%; ASD, 19%; HC, 21%).

CONCLUSION

We built a classifier from multiple protocol structural brain images applicable to independent samples from different clinical stages and spectra. The predictive information of the classifier could be useful for applying neuroimaging techniques to clinical differential diagnosis and predicting disease onset earlier.

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.

Genomic and neuroimaging approaches to bipolar disorder

BACKGROUND

To date, besides genome-wide association studies, a variety of other genetic analyses (e.g. polygenic risk scores, whole-exome sequencing and whole-genome sequencing) have been conducted, and a large amount of data has been gathered for investigating the involvement of common, rare and very rare types of DNA sequence variants in bipolar disorder. Also, non-invasive neuroimaging methods can be used to quantify changes in brain structure and function in patients with bipolar disorder.

AIMS

To provide a comprehensive assessment of genetic findings associated with bipolar disorder, based on the evaluation of different genomic approaches and neuroimaging studies.

METHOD

We conducted a PubMed search of all relevant literatures from the beginning to the present, by querying related search strings.

RESULTS

ANK3, CACNA1C, SYNE1, ODZ4 and TRANK1 are five genes that have been replicated as key gene candidates in bipolar disorder pathophysiology, through the investigated studies. The percentage of phenotypic variance explained by the identified variants is small (approximately 4.7%). Bipolar disorder polygenic risk scores are associated with other psychiatric phenotypes. The ENIGMA-BD studies show a replicable pattern of lower cortical thickness, altered white matter integrity and smaller subcortical volumes in bipolar disorder.

CONCLUSIONS

The low amount of explained phenotypic variance highlights the need for further large-scale investigations, especially among non-European populations, to achieve a more complete understanding of the genetic architecture of bipolar disorder and the missing heritability. Combining neuroimaging data with genetic data in large-scale studies might help researchers acquire a better knowledge of the engaged brain regions in bipolar disorder.

What we learn about bipolar disorder from large-scale neuroimaging: Findings and future directions from the ENIGMA Bipolar Disorder Working Group

MRI-derived brain measures offer a link between genes, the environment and behavior and have been widely studied in bipolar disorder (BD). However, many neuroimaging studies of BD have been underpowered, leading to varied results and uncertainty regarding effects. The Enhancing Neuro Imaging Genetics through Meta-Analysis (ENIGMA) Bipolar Disorder Working Group was formed in 2012 to empower discoveries, generate consensus findings and inform future hypothesis-driven studies of BD. Through this effort, over 150 researchers from 20 countries and 55 institutions pool data and resources to produce the largest neuroimaging studies of BD ever conducted. The ENIGMA Bipolar Disorder Working Group applies standardized processing and analysis techniques to empower large-scale meta- and mega-analyses of multimodal brain MRI and improve the replicability of studies relating brain variation to clinical and genetic data. Initial BD Working Group studies reveal widespread patterns of lower cortical thickness, subcortical volume and disrupted white matter integrity associated with BD. Findings also include mapping brain alterations of common medications like lithium, symptom patterns and clinical risk profiles and have provided further insights into the pathophysiological mechanisms of BD. Here we discuss key findings from the BD working group, its ongoing projects and future directions for large-scale, collaborative studies of mental illness.

Distinguish bipolar and major depressive disorder in adolescents based on multimodal neuroimaging: Results from the Adolescent Brain Cognitive Development study®

Background

Major depressive disorder and bipolar disorder in adolescents are prevalent and are associated with cognitive impairment, executive dysfunction, and increased mortality. Early intervention in the initial stages of major depressive disorder and bipolar disorder can significantly improve personal health.

Methods

We collected 309 samples from the Adolescent Brain Cognitive Development study, including 116 adolescents with bipolar disorder, 64 adolescents with major depressive disorder, and 129 healthy adolescents, and employed a support vector machine to develop classification models for identification. We developed a multimodal model, which combined functional connectivity of resting-state functional magnetic resonance imaging and four anatomical measures of structural magnetic resonance imaging (cortical thickness, area, volume, and sulcal depth). We measured the performances of both multimodal and single modality classifiers.

Results

The multimodal classifiers showed outstanding performance compared with all five single modalities, and they are 100% for major depressive disorder versus healthy controls, 100% for bipolar disorder versus healthy control, 98.5% (95% CI: 95.4–100%) for major depressive disorder versus bipolar disorder, 100% for major depressive disorder versus depressed bipolar disorder and the leave-one-site-out analysis results are 77.4%, 63.3%, 79.4%, and 81.7%, separately.

Conclusions

The study shows that multimodal classifiers show high classification performances. Moreover, cuneus may be a potential biomarker to differentiate major depressive disorder, bipolar disorder, and healthy adolescents. Overall, this study can form multimodal diagnostic prediction workflows for clinically feasible to make more precise diagnose at the early stage and potentially reduce loss of personal pain and public society.

Mega-analysis methods in ENIGMA: The experience of the generalized anxiety disorder working group

The ENIGMA group on Generalized Anxiety Disorder (ENIGMA-Anxiety/GAD) is part of a broader effort to investigate anxiety disorders using imaging and genetic data across multiple sites worldwide. The group is actively conducting a mega-analysis of a large number of brain structural scans. In this process, the group was confronted with many methodological challenges related to study planning and implementation, between-country transfer of subject-level data, quality control of a considerable amount of imaging data, and choices related to statistical methods and efficient use of resources. This report summarizes the background information and rationale for the various methodological decisions, as well as the approach taken to implement them. The goal is to document the approach and help guide other research groups working with large brain imaging data sets as they develop their own analytic pipelines for mega-analyses.

Brain structural associations with depression in a large early adolescent sample (the ABCD study®)

BACKGROUND

Depression is the leading cause of disability worldwide with > 50% of cases emerging before the age of 25 years. Large-scale neuroimaging studies in depression implicate robust structural brain differences in the disorder. However, most studies have been conducted in adults and therefore, the temporal origins of depression-related imaging features remain largely unknown. This has important implications for understanding aetiology and informing timings of potential intervention.

METHODS

Here, we examine associations between brain structure (cortical metrics and white matter microstructural integrity) and depression ratings (from caregiver and child), in a large sample (N = 8634) of early adolescents (9 to 11 years old) from the US-based, Adolescent Brain and Cognitive Development (ABCD) Study®. Data was collected from 2016 to 2018.

FINDINGS

We report significantly decreased global cortical and white matter metrics, and regionally in frontal, limbic and temporal areas in adolescent depression (Cohen's d = -0⋅018 to -0⋅041, β = -0·019 to -0⋅057). Further, we report consistently stronger imaging associations for caregiver-reported compared to child-reported depression ratings. Divergences between reports (caregiver vs child) were found to significantly relate to negative socio-environmental factors (e.g., family conflict, absolute β = 0⋅048 to 0⋅169).

INTERPRETATION

Depression ratings in early adolescence were associated with similar imaging findings to those seen in adult depression samples, suggesting neuroanatomical abnormalities may be present early in the disease course, arguing for the importance of early intervention. Associations between socio-environmental factors and reporter discrepancy warrant further consideration, both in the wider context of the assessment of adolescent psychopathology, and in relation to their role in aetiology.

FUNDING

Wellcome Trust (References: 104036/Z/14/Z and 220857/Z/20/Z) and the Medical Research Council (MRC, Reference: MC_PC_17209).

Association between body mass index and subcortical brain volumes in bipolar disorders-ENIGMA study in 2735 individuals

Individuals with bipolar disorders (BD) frequently suffer from obesity, which is often associated with neurostructural alterations. Yet, the effects of obesity on brain structure in BD are under-researched. We obtained MRI-derived brain subcortical volumes and body mass index (BMI) from 1134 BD and 1601 control individuals from 17 independent research sites within the ENIGMA-BD Working Group. We jointly modeled the effects of BD and BMI on subcortical volumes using mixed-effects modeling and tested for mediation of group differences by obesity using nonparametric bootstrapping. All models controlled for age, sex, hemisphere, total intracranial volume, and data collection site. Relative to controls, individuals with BD had significantly higher BMI, larger lateral ventricular volume, and smaller volumes of amygdala, hippocampus, pallidum, caudate, and thalamus. BMI was positively associated with ventricular and amygdala and negatively with pallidal volumes. When analyzed jointly, both BD and BMI remained associated with volumes of lateral ventricles  and amygdala. Adjusting for BMI decreased the BD vs control differences in ventricular volume. Specifically, 18.41% of the association between BD and ventricular volume was mediated by BMI (Z = 2.73, p = 0.006). BMI was associated with similar regional brain volumes as BD, including lateral ventricles, amygdala, and pallidum. Higher BMI may in part account for larger ventricles, one of the most replicated findings in BD. Comorbidity with obesity could explain why neurostructural alterations are more pronounced in some individuals with BD. Future prospective brain imaging studies should investigate whether obesity could be a modifiable risk factor for neuroprogression.

Associations between brain structure and sleep patterns across adolescent development

STUDY OBJECTIVES

Structural brain maturation and sleep are complex processes that exhibit significant changes over adolescence and are linked to many physical and mental health outcomes. We investigated whether sleep-gray matter relationships are developmentally invariant (i.e. stable across age) or developmentally specific (i.e. only present during discrete time windows) from late childhood through young adulthood.

METHODS

We constructed the Neuroimaging and Pediatric Sleep Databank from eight research studies conducted at the University of Pittsburgh (2009-2020). Participants completed a T1-weighted structural MRI scan (sMRI) and 5-7 days of wrist actigraphy to assess naturalistic sleep. The final analytic sample consisted of 225 participants without current psychiatric diagnoses (9-25 years). We extracted cortical thickness and subcortical volumes from sMRI. Sleep patterns (duration, timing, continuity, regularity) were estimated from wrist actigraphy. Using regularized regression, we examined cross-sectional associations between sMRI measures and sleep patterns, as well as the effects of age, sex, and their interaction with sMRI measures on sleep.

RESULTS

Shorter sleep duration, later sleep timing, and poorer sleep continuity were associated with thinner cortex and altered subcortical volumes in diverse brain regions across adolescence. In a discrete subset of regions (e.g. posterior cingulate), thinner cortex was associated with these sleep patterns from late childhood through early-to-mid adolescence but not in late adolescence and young adulthood.

CONCLUSIONS

In childhood and adolescence, developmentally invariant and developmentally specific associations exist between sleep patterns and gray matter structure, across brain regions linked to sensory, cognitive, and emotional processes. Sleep intervention during specific developmental periods could potentially promote healthier neurodevelopmental outcomes.

Individuals at increased risk for development of bipolar disorder display structural alterations similar to people with manifest disease

In psychiatry, there has been a growing focus on identifying at-risk populations. For schizophrenia, these efforts have led to the development of early recognition and intervention measures. Despite a similar disease burden, the populations at risk of bipolar disorder have not been sufficiently characterized. Within the BipoLife consortium, we used magnetic resonance imaging (MRI) data from a multicenter study to assess structural gray matter alterations in N = 263 help-seeking individuals from seven study sites. We defined the risk using the EPIbipolar assessment tool as no-risk, low-risk, and high-risk and used a region-of-interest approach (ROI) based on the results of two large-scale multicenter studies of bipolar disorder by the ENIGMA working group. We detected significant differences in the thickness of the left pars opercularis (Cohen's d = 0.47, p = 0.024) between groups. The cortex was significantly thinner in high-risk individuals compared to those in the no-risk group (p = 0.011). We detected no differences in the hippocampal volume. Exploratory analyses revealed no significant differences in other cortical or subcortical regions. The thinner cortex in help-seeking individuals at risk of bipolar disorder is in line with previous findings in patients with the established disorder and corresponds to the region of the highest effect size in the ENIGMA study of cortical alterations. Structural alterations in prefrontal cortex might be a trait marker of bipolar risk. This is the largest structural MRI study of help-seeking individuals at increased risk of bipolar disorder.

Brain/MINDS beyond human brain MRI project: A protocol for multi-level harmonization across brain disorders throughout the lifespan

Psychiatric and neurological disorders are afflictions of the brain that can affect individuals throughout their lifespan. Many brain magnetic resonance imaging (MRI) studies have been conducted; however, imaging-based biomarkers are not yet well established for diagnostic and therapeutic use. This article describes an outline of the planned study, the Brain/MINDS Beyond human brain MRI project (BMB-HBM, FY2018 ~ FY2023), which aims to establish clinically-relevant imaging biomarkers with multi-site harmonization by collecting data from healthy traveling subjects (TS) at 13 research sites. Collection of data in psychiatric and neurological disorders across the lifespan is also scheduled at 13 sites, whereas designing measurement procedures, developing and analyzing neuroimaging protocols, and databasing are done at three research sites. A high-quality scanning protocol, Harmonization Protocol (HARP), was established for five high-quality 3 T scanners to obtain multimodal brain images including T1 and T2-weighted, resting-state and task functional and diffusion-weighted MRI. Data are preprocessed and analyzed using approaches developed by the Human Connectome Project. Preliminary results in 30 TS demonstrated cortical thickness, myelin, functional connectivity measures are comparable across 5 scanners, suggesting sensitivity to subject-specific connectome. A total of 75 TS and more than two thousand patients with various psychiatric and neurological disorders are scheduled to participate in the project, allowing a mixed model statistical harmonization. The HARP protocols are publicly available online, and all the imaging, demographic and clinical information, harmonizing database will also be made available by 2024. To the best of our knowledge, this is the first project to implement a prospective, multi-level harmonization protocol with multi-site TS data. It explores intractable brain disorders across the lifespan and may help to identify the disease-specific pathophysiology and imaging biomarkers for clinical practice.