The human nervous system itself and its extensive connection with the human body are complex. There are various representations of nervous system with diverse observation methods and multiple dimensions of metrics. Similarly, in the field of medicine, almost all clinical diagnostic protocols for neuropsychiatric diseases/disorders involve multiple dimensions of individual characteristics. With the recent development of technology, scientists have been able to develop a more comprehensive understanding of neuropsychiatric disorders from multiple scales and dimensions. For instance, high spatial resolution MRI, high temporal resolution EEG/MEG and ecologically valid near infrared spectroscopy (NIRS) provide reliable methods for exploring brain structure and function. In addition, eye movements, body movements, skin conductance and dynamic heart rate can objectively measure individual behavior and emotion and provide novel insights for the characterization of the individual nervous system. More importantly, advances in algorithms and analytics allow us to discover even more valuable indicators of neuropsychiatric disorders from current data. These advanced technologies, combining with the symptom and the generic risk measurements, could bring new insight into the nervous system, as well as diseased brains.
The goal of this research topic is to promote the novel data analysis methodologies and innovative investigation paradigms into multi-scale, multidimensional characterization of the neuropsychiatric diseases/disorders (depression, anxiety disorder, obsessive-compulsive disorder, schizophrenia, Tourette syndrome, attention deficit and hyperactivity disorder, autism spectrum disorder, Alzheimer’s disease, etc.), as well as their potential clinical applications.
Research areas to be covered by this Research Topic include, but are not limited to:
-Discovery of the biomarkers with pathological significance related to neuropsychiatric disorders and the possible connection between them, using modalities such as MRI, EEG/MEG, NIRS, eye movements, body movement, skin conductivity, dynamic heart rate and other techniques.
-Data-driven characterization of the neuropsychiatric disorders with imaging, behaviour, and physiological biomarkers by statistical and machine learning approaches, and their application in diagnosis / differential diagnosis/treatment efficacy studies.
-Solutions for the fusion and integrated analysis of multi-dimensional biomarkers collected from heterogeneous sources, and the analysis of the interaction between different biomarkers, using advanced machine learning methods such as deep neural networks and representation learning on the graphs.
-Novel algorithms and analytics frameworks adaptive to data collected from multiple scales, both spatial and temporal, for analysing the individual and groupwise nervous system at scales.
Review articles and comments are also welcomed.
The human nervous system itself and its extensive connection with the human body are complex. There are various representations of nervous system with diverse observation methods and multiple dimensions of metrics. Similarly, in the field of medicine, almost all clinical diagnostic protocols for neuropsychiatric diseases/disorders involve multiple dimensions of individual characteristics. With the recent development of technology, scientists have been able to develop a more comprehensive understanding of neuropsychiatric disorders from multiple scales and dimensions. For instance, high spatial resolution MRI, high temporal resolution EEG/MEG and ecologically valid near infrared spectroscopy (NIRS) provide reliable methods for exploring brain structure and function. In addition, eye movements, body movements, skin conductance and dynamic heart rate can objectively measure individual behavior and emotion and provide novel insights for the characterization of the individual nervous system. More importantly, advances in algorithms and analytics allow us to discover even more valuable indicators of neuropsychiatric disorders from current data. These advanced technologies, combining with the symptom and the generic risk measurements, could bring new insight into the nervous system, as well as diseased brains.
The goal of this research topic is to promote the novel data analysis methodologies and innovative investigation paradigms into multi-scale, multidimensional characterization of the neuropsychiatric diseases/disorders (depression, anxiety disorder, obsessive-compulsive disorder, schizophrenia, Tourette syndrome, attention deficit and hyperactivity disorder, autism spectrum disorder, Alzheimer’s disease, etc.), as well as their potential clinical applications.
Research areas to be covered by this Research Topic include, but are not limited to:
-Discovery of the biomarkers with pathological significance related to neuropsychiatric disorders and the possible connection between them, using modalities such as MRI, EEG/MEG, NIRS, eye movements, body movement, skin conductivity, dynamic heart rate and other techniques.
-Data-driven characterization of the neuropsychiatric disorders with imaging, behaviour, and physiological biomarkers by statistical and machine learning approaches, and their application in diagnosis / differential diagnosis/treatment efficacy studies.
-Solutions for the fusion and integrated analysis of multi-dimensional biomarkers collected from heterogeneous sources, and the analysis of the interaction between different biomarkers, using advanced machine learning methods such as deep neural networks and representation learning on the graphs.
-Novel algorithms and analytics frameworks adaptive to data collected from multiple scales, both spatial and temporal, for analysing the individual and groupwise nervous system at scales.
Review articles and comments are also welcomed.