Computationally assisted diagnosis of Alzheimer's dementia

With approximately 48 million affected patients and annual costs of 600 billion dollars, dementia is one of the major global health challenges.  Alzheimer's dementia (AD), the most frequent reason for cognitive decline, is diagnosed based on clinical and neuropsychological criteria, lumbar puncture and MRI scans are additionally employed for differential diagnosis. Today, no causal treatment of AD is available but various potential disease modifying drugs (DMDs) are in development. An approval of an effective DMD for AD would represent a revolution in dementia treatment and dramatically increase the need for save and cheap diagnostic tools. We have shown recently that applying state-of-the-art machine learning algorithms to the results of an optimized neuropsychological test battery enables discrimination between AD and other reasons for cognitive decline that was at least as accurate as that based on expensive and risky techniques such as MRI or lumbar puncture

Principle Investigators: Pavel GurevichHannes Stuke

Collaboration partners: 
Prof. Helmut Hildebrandt (Municipal Hospital of Bremen-OstUniversity of Oldenburg),
Dr. Heiner Stuke (Charité Berlin)


Publications

Gurevich P., Stuke H., Kastrup A., Stuke H. and Hildebrandt H. 
Neuropsychological testing and machine learning distinguish Alzheimer's disease from other causes for cognitive impairment.
 
Front. Aging Neurosci. 9:114 (2017) 
(pdf)