Fusible evolutionary deep neural network mixture learning from distributed data for robust medical...
Many brain diseases are characterized by behavioural symptoms, which can be devastating to the patient. Some neurological brain diseases, such as Alzheimer’s disease or other dementias, and virtually all psychiatric diseases, for example schizophrenia, are even formally defined by behavioural symptoms.
It is therefore of paramount importance for clinicians and researchers in clinical neuropsychology and related disciplines, especially neurology and psychiatry, to have sensitive methods at their disposal to evaluate the behavioural symptoms necessary for diagnosis, or to assess the behavioural sequels of disease and treatment outcome. Behavioural patient characteristics are also important in several other branches of health research. Chemotherapy or cardiac surgery, to name a few examples, may have cognitive side effects or other behavioural sequels, such as fatigue or apathy.
Many well-validated neuropsychological tests assist clinical researchers and practitioners in the diagnosis of neurologic and psychiatric patients, and in evaluating treatments for brain diseases and psychiatric disorders. However, these tests are typically stand-alone instruments, whereas diagnostic and evaluative tasks are of a multivariate nature. That is, brain diseases and psychiatric disorders reveal themselves in complex syndromes of multiple behavioural symptoms.
Modern statistical methods can solve such multivariate problems, provided the availability of a large multivariate normative databank of neuropsychological tests. Such data are up to now hidden in numerous research projects that have been conducted in the last decades. A goldmine of control data is hidden in the desks and computers of researchers. It only has to be extracted for exploitation.
Fortunately, the attitudes on data sharing are changing. Large-scale projects often have formal data sharing policies, and researchers in small-scale studies are increasingly prepared to share their data. This project will make this data accessible, useful, and insightful by building an Advanced Neuropsychological Diagnostics Infrastructure (ANDI).
ANDI will allow researchers to more easily locate patients in their samples who, for example, fulfil particular diagnostic criteria, are cognitively impaired or otherwise show an abnormal pattern of cognitive or behavioural characteristics, respond particularly well to a treatment, et cetera. The ANDI database and analysis tools will be made accessible via a web application and web services.