Machine Learning in Neurological and Psychiatric Disorders: A Promising Appro...

SAY

Machine Learning in Neurological and Psychiatric Disorders: A Promising Approach for Clinical Assessment and Prediction

Call for Papers
Machine learning techniques have emerged as a promising approach in clinical neuROScience. Most imaging data is highly complex with subtle features reflecting the underlying complexity of the human brain, as well as the complexity of the spatial and temporal dynamical feature changes associated with neurological and psychiatric disorders. It has become increasingly evident that relying on simple approaches, such as peak activation, EEG epileptic spikes, region of interest analysis, is not sufficient to provide the outcome needed to explore the complexity of disease-related pathological alterations of brain functions and to accurately and reliably diagnose and classify neurological and psychiatric disorders.

Furthermore, effective treatments for many of these disorders require early detection and reliable prediction. An accurate prediction, in turn, requires detection of many subtle brain and behavioral features that are unlikely to be accurately assessed using simple techniques. Multimodal imaging and behavioral data must be combined and classified objectively to provide a reliable prediction. Machine learning techniques are suited to exactly solve this problem. While many imaging studies have relied on group-averaged data due to the subtle nature of feature differences between healthy controls and patient populations, such approaches do not allow the clinical diagnosis of single subjects. Instead, machine learning techniques are able to utilize numerous imaging and behavioral features from single-subject data to effectively and objectively diagnose their brain state.

The purpose of this issue is to encourage this development by inviting original research as well as review articles along these lines.

Potential topics include, but are not limited to:

    Machine learning for the detection and classification of fMRI, MEG, EEG, and iEEG spatiotemporal patterns of brain activity
    Machine learning in the classification of epilepsy types
    Automation of clinical assessments via machine learning techniques
    Machine learning in mental-state monitoring from real-time EEG-analysis
    Machine learning approaches for the integration of multimodal imaging data
    Machine learning approaches for the integration of behavioral data
    Machine learning approaches for integrating clinical and imaging features in the diagnosis of neurological and psychiatric disorders
    Anatomical shape analysis using machine learning techniques for the diagnosis of neurodegenerative diseases
    Performance comparisons of machine learning algorithms applied to neurological and psychiatric disorders

Authors can submit their manuscripts via the Manuscript Tracking System at http://mts.hindawi.com/submit/journals/bn/mlnp/.
Manuscript Due        Friday, 27 May 2016
First Round of Reviews        Friday, 19 August 2016
Publication Date        Friday, 14 October 2016
Lead Guest Editor

    Maher Quraan, University of Toronto, Toronto, Canada

Guest Editors

    Michael Nitsche, Leibniz Research Centre for Working Environment and Human Factors, Dortmund, Germany
    Taufik Valiante, Toronto Western Hospital, Toronto, Canada
    Ismail Mohamed, Dalhousie University, Halifax, Canada