Computational neuroscience approach to biomarkers and treatments for mental disorders

Abstract

Psychiatry research has long experienced a stagnation stemming from a lack of understanding of the neurobiological underpinnings of phenomenologically defined mental disorders. Recently, the application of computational neuroscience to psychiatry research has shown great promise in establishing a link between phenomenological and pathophysiological aspects of mental disorders, thereby recasting current nosology in more biologically meaningful dimensions. In this review, we highlight recent investigations into computational neuroscience that have undertaken either theory-or data-driven approaches to quantitatively delineate the mechanisms of mental disorders. The theory-driven approach, including reinforcement learning models, plays an integrative role in this process by enabling correspondence between behavior and disorderspecific alterations at multiple levels of brain organization, ranging from molecules to cells to circuits. Previous studies have explicated a plethora of defining symptoms of mental disorders, including anhedonia, inattention, and poor executive function. The data-driven approach, on the other hand, is an emerging field in computational neuroscience seeking to identify disorder-specific features among high-dimensional big data. Remarkably, various machine-learning techniques have been applied to neuroimaging data, and the extracted disorderspecific features have been used for automatic casecontrol classification. For many disorders, the reported accuracies have reached 90% or more. However, we note that rigorous tests on independent cohorts are critically required to translate this research into clinical applications. Finally, we discuss the utility of the disorder-specific features found by the data-driven approach to psychiatric therapies, including neurofeedback. Such developments will allow simultaneous diagnosis and treatment of mental disorders using neuroimaging, thereby establishing 'theranostics' for the first time in clinical psychiatry.

Advances in fMRI Real-Time Neurofeedback

“…Regrettably, early studies of biomarkers suffered from overfitting of machine learning algorithms and did not exhibit generalization capability for completely independent validation cohorts [70–74]. However, the recent development of sophisticated machine learning algorithms has overcome these technical problems and led to the production of rs-fcMRI-based biomarkers, which are capable of classifying patients from controls with high accuracy and generalization to completely independent cohorts [32–34,75]. Development of these robust rs-fcMRI-based biomarkers have allowed FCNef, which is also rs-fcMRI-based, to directly modify them.…”

“…Considering these advantages, FCNef has produced preliminary but encouraging therapeutic results with depression patients as well as with adults with high-functioning autism spectrum disorder (ASD) [34,36,75]. With regards to depression, abnormally more positive functional connectivity between the left dorsolateral prefrontal cortex and left precuneus/posterior cingulate cortex was found to play the most crucial role in patients with high depression scores and melancholic depression [32].…”

MOU-EC: model-based whole-brain effective connectivity to extract biomarkers for brain dynamics from fMRI data and study distributed cognition

“…Importantly, many neural diseases are likely to affect multiple brain regions and thus require adequate tools to capture their distributed nature. Another direction 715 where machine learning is a key tool is the development of personalized medicine, adapting the models to individual patients beyond group analyses [155].…”

Making psychiatry a clinical neuroscience‐based medicine

“…A. Lieberman wrote in his book, Shrinks: The Untold Story of Psychiatry , psychiatry has developed from a ‘cult of shrinks into a scientific medicine of the brain.’ Discovery of the neurochemical basis of the effect of psychotropic drugs was the first breakthrough in the scientific understanding of mental disorders. Subsequently, functional magnetic resonance imaging studies have succeeded in connecting phenomena of the mind to that in the brain, which has led to the promising new treatment strategy of neurofeedback . Recent genome‐wide association studies have shown the utility of polygenic risk scores (PRS), and analyses using PRS have confirmed traditional clinical findings, for example, early age at onset in major depression as a risk factor of bipolar disorder .…”

“…However, such remarkable progress has not yet caused innovation in clinical practice in psychiatry, and daily practice in clinics is mostly similar to that of several decades ago. Paradoxically, the progress of biological research has obscured the boundary of diagnostic categories: The same classes of drugs are effective for different types of diseases and there is an overlap in genetic, neuroimaging, and cellular findings across different mental disorders . This may indicate that current biological studies in psychiatry have not grown out of understanding mental disorders’ symptomatic‐level phenomena.…”