Data-Driven Strategies in Neurodegenerative Diseases: Advancing Drug Development and Disease Management

Abstract

Neurodegenerative Disorders, including Alzheimer's, Parkinson's, and Huntington's Disease, pose major challenges to modern medicine due to their progressive nature and impact on patients and the healthcare system. These disorders lead to declines in cognitive, motor, and functional capabilities due to gradual neuron degeneration. Despite extensive research, effective disease-modifying therapies remain elusive, hindered by the complexity of identifying suitable therapeutic targets and the heterogeneity of each condition.<br/>

This thesis addresses critical challenges within the pharmaceutical value chain using data-driven methodologies, including machine learning and artificial intelligence, to develop innovative strategies for personalized medical treatments and improved disease management. A key challenge lies in identifying appropriate target structures for active substances. A systems biology approach leverages advanced data analytics for an in-depth analysis of complex interactions within biological pathways, enhancing the understanding of disease mechanisms and guiding the search for effective treatments. Furthermore, determining the appropriate timing and patient selection for treatment is essential. The heterogeneity of symptom progression in Huntington's Disease is examined, identifying two distinct progression subtypes with significant cognitive performance differences. These findings underscore the need for personalized treatment strategies based on individual progression patterns and the importance of recognizing symptom diversity that influences clinical outcomes. Additionally, objective measurements are investigated by evaluating gait sensor data for monitoring symptoms and their progression in Parkinson's Disease. The feasibility of using sensor-based digital gait data as endpoints in clinical trials is assessed by determining necessary sample sizes and measurement effectiveness. This approach aims to establish a reliable framework for integrating health technologies into clinical practice, enhancing patient monitoring and outcomes.<br/>

In conclusion, the results of this thesis underscore the potential of data-driven methods in developing disease-modifying treatments for neurodegenerative diseases. Insights gained contribute to understanding potential drug targets, disease progression heterogeneity, and the utility of digital sensors for monitoring, paving the way for more effective drug development and personalized disease management.