Personalized Combination Therapy for AD with Common Comorbidities

University Of Pittsburgh At Pittsburgh, Pittsburgh PA

Investigators

Linked publications & trials

Abstract

Project summary Our goal is to develop artificial intelligent (AI) analytics models to facilitate personalized treatment plans for Alzheimer?s disease (AD) patients with most common comorbidities, such as cardiovascular diseases (CVD), diabetes mellitus (DM) and depression. AD is a neurodegenerative disease that progressively causes memory loss and cognitive impairment. While current treatments have shown some amelioration of symptoms, the effects have been transient and limited to a small percentage of patients. Moreover, disease-modifying drugs based on our current understanding of disease mechanisms have all shown negative results in clinical trials. Part of the failure is due to the heterogeneity in the disease mechanism, of which we do not yet have a clear understanding. Additionally, increasing evidence has indicated that comorbidities of AD share common disease pathways with AD, and medications used for these diseases may also alter the cognitive functions in AD patients. However, few studies have assessed combinations of these medications in treatments for AD. In this study, we will address this problem by retrospectively analyzing the observational data collected by the University of Pittsburgh Alzheimer?s Disease Research Center (ADRC). In Aim 1, we plan to statistically investigate the effects of different medications when used in combination with anti-AD medications on the trajectory of cognitive decline. If specific drug combination(s) are found to have a potential synergistic effect against cognitive decline, we will further study the underlying mechanisms using molecular systems pharmacology methods in Aim 2. In Aim 3, we will focus on establishing a clinical decision support system that facilitates individualized treatment for AD patients with these common comorbidities. We will build a Bayesian Network model that can predict the disease progression based patient and treatment information provided by the ADRC data set. The model will be learned and tested based on the ADRC dataset using the Tetrad software package. We will then apply methodologies of decision theory and search for a treatment combination that leads to the optimal treatment outcomes for specific patients. Collectively, these studies will contribute to a discovery of novel drug combinations for treating AD patients with comorbidities, and generate ideas for a clinical decision support system that can facilitate personalized medicine for these patients.