Leveraging Observational and RCT Data for Understanding Interventions’ efficacy: Applications in Progressive and Acute Neurological Diseases

The advancement of drug repurposing for progressive and acute neurological diseases is hampered by the limitations of randomized clinical trials (RCTs) and observational data. This dissertation presents a comprehensive framework to integrate data-driven insights from multiple sources, including observational studies, RCTs, and synthetic data generation, to overcome these challenges. The first study focuses on estimating treatment effects on the population level, which investigates the effects of routine and high-dose influenza vaccines on the risk of Alzheimer’s Disease and Related Dementias (ADRD) through a trial emulation framework applied to health claims data, addressing biases inherent in observational studies. The second study develops an interpretable framework for estimating heterogeneous treatment effects, enabling the identification of responsive subgroups from failed clinical trials and supporting personalized therapeutic strategies. Lastly, the third study introduces a novel generative approach leveraging Large Language Models (LLMs) and causal graphs for synthesizing high-quality tabular data in low-data regimes, addressing the challenges of small sample sizes and enhancing the robustness of clinical insights. By bridging gaps between data availability, treatment effect estimation, and personalized medicine, this dissertation contributes to advancing the precision of drug repurposing strategies for complex neurological conditions. Future work will extend the proposed frameworks to broader clinical domains, further validating their efficacy and applicability.