Identifying multimodal signatures associated with symptom clusters: the example of the IMAGEMEND project

Statistical and Machine Learning Analysis in Brain-Imaging Genetics: A Review of Methods

Brain-imaging-genetic analysis is an emerging field of research that aims at aggregating data from neuroimaging modalities, which characterize brain structure or function, and genetic data, which capture the structure and function of the genome, to explain or predict normal (or abnormal) brain performance. Brain-imaging-genetic studies offer great potential for understanding complex brain-related diseases/disorders of genetic etiology. Still, a combined brain-wide genome-wide analysis is difficult to perform as typical datasets fuse multiple modalities, each with high dimensionality, unique correlational landscapes, and often low statistical signal-to-noise ratios. In this review, we outline the progress in brain-imaging-genetic methodologies starting from early massive univariate to current deep learning approaches, highlighting each approach's strengths and weaknesses and elongating it with the field's development. We conclude by discussing selected remaining challenges and prospects for the field.

Advancing translational research in neuroscience through multi-task learning

Translational research in neuroscience is increasingly focusing on the analysis of multi-modal data, in order to account for the biological complexity of suspected disease mechanisms. Recent advances in machine learning have the potential to substantially advance such translational research through the simultaneous analysis of different data modalities. This review focuses on one of such approaches, the so-called "multi-task learning" (MTL), and describes its potential utility for multi-modal data analyses in neuroscience. We summarize the methodological development of MTL starting from conventional machine learning, and present several scenarios that appear particularly suitable for its application. For these scenarios, we highlight different types of MTL algorithms, discuss emerging technological adaptations, and provide a step-by-step guide for readers to apply the MTL approach in their own studies. With its ability to simultaneously analyze multiple data modalities, MTL may become an important element of the analytics repertoire used in future neuroscience research and beyond.

Consortium on Vulnerability to Externalizing Disorders and Addictions (cVEDA): A developmental cohort study protocol

BACKGROUND

Low and middle-income countries like India with a large youth population experience a different environment from that of high-income countries. The Consortium on Vulnerability to Externalizing Disorders and Addictions (cVEDA), based in India, aims to examine environmental influences on genomic variations, neurodevelopmental trajectories and vulnerability to psychopathology, with a focus on externalizing disorders.

METHODS

cVEDA is a longitudinal cohort study, with planned missingness design for yearly follow-up. Participants have been recruited from multi-site tertiary care mental health settings, local communities, schools and colleges. 10,000 individuals between 6 and 23 years of age, of all genders, representing five geographically, ethnically, and socio-culturally distinct regions in India, and exposures to variations in early life adversity (psychosocial, nutritional, toxic exposures, slum-habitats, socio-political conflicts, urban/rural living, mental illness in the family) have been assessed using age-appropriate instruments to capture socio-demographic information, temperament, environmental exposures, parenting, psychiatric morbidity, and neuropsychological functioning. Blood/saliva and urine samples have been collected for genetic, epigenetic and toxicological (heavy metals, volatile organic compounds) studies. Structural (T1, T2, DTI) and functional (resting state fMRI) MRI brain scans have been performed on approximately 15% of the individuals. All data and biological samples are maintained in a databank and biobank, respectively.

DISCUSSION

The cVEDA has established the largest neurodevelopmental database in India, comparable to global datasets, with detailed environmental characterization. This should permit identification of environmental and genetic vulnerabilities to psychopathology within a developmental framework. Neuroimaging and neuropsychological data from this study are already yielding insights on brain growth and maturation patterns.

Reproducible grey matter patterns index a multivariate, global alteration of brain structure in schizophrenia and bipolar disorder

Schizophrenia is a severe mental disorder characterized by numerous subtle changes in brain structure and function. Machine learning allows exploring the utility of combining structural and functional brain magnetic resonance imaging (MRI) measures for diagnostic application, but this approach has been hampered by sample size limitations and lack of differential diagnostic data. Here, we performed a multi-site machine learning analysis to explore brain structural patterns of T1 MRI data in 2668 individuals with schizophrenia, bipolar disorder or attention-deficit/ hyperactivity disorder, and healthy controls. We found reproducible changes of structural parameters in schizophrenia that yielded a classification accuracy of up to 76% and provided discrimination from ADHD, through it lacked specificity against bipolar disorder. The observed changes largely indexed distributed grey matter alterations that could be represented through a combination of several global brain-structural parameters. This multi-site machine learning study identified a brain-structural signature that could reproducibly differentiate schizophrenia patients from controls, but lacked specificity against bipolar disorder. While this currently limits the clinical utility of the identified signature, the present study highlights that the underlying alterations index substantial global grey matter changes in psychotic disorders, reflecting the biological similarity of these conditions, and provide a roadmap for future exploration of brain structural alterations in psychiatric patients.

From neuroscience to evidence based psychological treatments - The promise and the challenge, ECNP March 2016, Nice, France

This ECNP meeting was designed to build bridges between different constituencies of mental illness treatment researchers from a range of backgrounds with a specific focus on enhancing the development of novel, evidence based, psychological treatments. In particular we wished to explore the potential for basic neuroscience to support the development of more effective psychological treatments, just as this approach is starting to illuminate the actions of drugs. To fulfil this aim, a selection of clinical psychologists, psychiatrists and neuroscientists were invited to sit at the same table. The starting point of the meeting was the proposition that we know certain psychological treatments work, but we have only an approximate understanding of why they work. The first task in developing a coherent mental health science would therefore be to uncover the mechanisms (at all levels of analysis) of effective psychological treatments. Delineating these mechanisms, a task that will require input from both the clinic and the laboratory, will provide a key foundation for the rational optimisation of psychological treatments. As reviewed in this paper, the speakers at the meeting reviewed recent advances in the understanding of clinical and cognitive psychology, neuroscience, experimental psychopathology, and treatment delivery technology focussed primarily on anxiety disorders and depression. We started by asking three rhetorical questions: What has psychology done for treatment? What has technology done for psychology? What has neuroscience done for psychology? We then addressed how research in five broad research areas could inform the future development of better treatments: Attention, Conditioning, Compulsions and addiction, Emotional Memory, and Reward and emotional bias. Research in all these areas (and more) can be harnessed to neuroscience since psychological therapies are a learning process with a biological basis in the brain. Because current treatment approaches are not fully satisfactory, there is an imperative to understand why not. And when psychological therapies do work we need to understand why this is the case, and how we can improve them. We may be able to improve accessibility to treatment without understanding mechanisms. But for treatment innovation and improvement, mechanistic insights may actually help. Applying neuroscience in this way will become an additional mission for ECNP.

Association of Inter-individual Differences in Imaging Markers with Schizophrenia Phenotypes

Introduction

Neuroimaging studies have identified several candidate biomarkers of schizophrenia. However, it is unclear whether the considerable variability in these neurobiological correlates between patients can be translated into the clinical setting.

Objectives

We aimed to identify neuroimaging predictors of clinical course in patients with schizophrenia. Combined with the identification of genetically determined markers of schizophrenia risk, our studies aimed to elucidate the biological basis and the clinical relevance of inter-individual variability between patients.

Methods

We included over 150 patients with schizophrenia and 279 healthy volunteers across five neuroimaging centers in the framework of the IMAGEMEND project [1]. We performed multiple studies on MRI scans using random forests and ROC curves to predict clinical course. Data from healthy controls served to normalize the data from the clinical population and to provide a benchmark for the findings.

Results

We identified ensembles of neuroimaging markers and of genetic variants predictive of clinical course. Results highlight that (i) brain imaging carries significant clinical information, (ii) clinical information at baseline can considerably increase prediction accuracy.

Conclusion

The methodological challenges and the results will be discussed in the context of recent findings from other multi-site studies. We conclude that brain imaging data on their own right are relevant to stratify patients in terms of clinical course; however, complementing these data with other modalities such as genetics and clinical information is necessary to further develop the field towards clinical application of the predictions.

Disclosure of interest

Giulio Pergola is the academic supervisor of a Hoffmann-La Roche Collaboration grant that partially funds his salary.

Epistasis in Neuropsychiatric Disorders

The contribution of epistasis to human disease remains unclear. However, several studies have now identified epistatic interactions between common variants that increase the risk of a neuropsychiatric disorder, while there is growing evidence that genetic interactions contribute to the pathogenicity of rare, multigenic copy-number variants (CNVs) that have been observed in patients. This review discusses the current evidence for epistatic events and genetic interactions in neuropsychiatric disorders, how paradigm shifts in the phenotypic classification of patients would empower the search for epistatic effects, and how network and cellular models might be employed to further elucidate relevant epistatic interactions.