Precision prediction of Alzheimer’s risk in women: Leveraging female-specific variables and machine learning for risk reduction

Project Summary

Alzheimer’s disease (AD) disproportionately affects women, yet most AD risk prediction models overlook female-specific factors, particularly those related to menopause. Menopause, characterized by a significant decline in ovarian hormones, represents a key transition point in the aging trajectory that significantly impacts brain health, influencing neuroplasticity, metabolism, and inflammation. However, many studies aggregate data by sex or exclude menopause-related variables, leading to underestimation of AD risk in women. This project aims to fill these gaps by using large-scale data to develop a predictive machine learning model tailored to women’s unique AD risk factors. The study will examine how menopause-related variables, like symptom profiles and menopausal hormone therapy (MHT) types, contribute to AD risk, and create a tool to identify women at high risk based on their symptoms, hormone exposure, and genetics.