Advancing Alzheimer’s Research through Multimodal Data and Digital Innovation
Hariri Institute Junior Faculty Fellow Spotlight: Huitong Ding, Research Assistant Professor, Chobanian & Avedisian School of Medicine
For Dr. Huitong Ding, the path to understanding Alzheimer’s disease runs through the data that captures everyday life—how people speak, sleep, move, and think. As a Research Assistant Professor in the Department of Anatomy & Neurobiology at the Chobanian & Avedisian School of Medicine and investigator at the Framingham Heart Study, Ding’s research bridges data science, digital health, and Alzheimer’s disease (AD), with a focus on better understanding and predicting diverse ways AD manifests and progresses across populations.
Collaborating globally with interdisciplinary teams across academia and industry, his work integrates diverse populations, interdisciplinary methods, and digital phenotyping tools such as speech analysis, mobile assessments, and wearable sensors with the aim of developing personalized, data-driven models to predict AD risk over a lifetime. Recent work has shown that digital devices tracking activity, sleep, cognitive tasks, and voice can reliably reflect cognitive health, laying the foundation for scalable, real-time monitoring of cognitive decline.
Professor Ding was awarded a 2025 Junior Faculty Fellowship from Hariri Institute last spring. He spoke with us about the ideas behind his research and his vision for what comes next.
Can you describe your research focus and its applications?
I am committed to advancing inclusive and translational research in Alzheimer’s disease (AD) by integrating diverse populations and interdisciplinary methodologies. My research focuses on characterizing the cognitive heterogeneity of AD, uncovering sex-specific patterns of disease progression, and identifying early, modifiable risk factors. To improve early detection and monitoring of cognitive decline, my work leverages digital phenotyping tools—including speech, sensor-based devices, and mobile assessments—to capture subtle behavioral and cognitive changes.
A central goal of my work is to leverage existing multimodal and longitudinal cohort data to develop dynamic, personalized models for predicting an individual’s lifetime risk of AD. In parallel, I aim to deploy digital devices to continuously collect novel, digital versions of health indicators—such as cognitive, behavioral, and physiological signals—enabling real-time monitoring and early detection of disease-related changes from the variability of these signals. My ongoing research also places strong emphasis on the heart-brain connection, systematically examining how cardiovascular health shapes brain aging lifespan trajectories and contributes to AD risk. This integrative approach supports the development of scalable and proactive strategies for AD risk stratification and prevention.
How did you become interested in this? Was there something that inspired this area of interest?
In the context of rapid population aging, AD and other cognitive disorders have become increasingly prevalent. However, in many resource-limited settings, access to effective cognitive screening and early detection remains a significant challenge. This motivated me to explore how analytical methods, diverse data sources, and emerging digital technologies can be integrated to develop inclusive and scalable approaches for early detection approaches that are accessible across diverse populations and adaptable to non-clinical settings.
What are the main goals or objectives of your research?
The primary objectives of my research are to improve early detection, enhance risk stratification, and promote equitable prevention of AD across diverse populations. I aim to achieve this by (1) characterizing cognitive heterogeneity and identifying sex-specific and modifiable risk factors, (2) developing personalized models for lifetime AD risk prediction using multimodal and longitudinal data, and (3) advancing the use of digital technologies to capture scalable, real-time cognitive markers.
Has there been a recent development or finding that you find particularly exciting?
Our team is actively validating the feasibility and reliability of using various digital devices to capture health-related indicators, including physical activity, sleep patterns, smartphone-based cognitive tasks, digital clock drawing test, and human voice features. We are systematically assessing the validity of these digital measures and establishing their associations with cognitive health in our studies such as Passive Measures of Physical Activity and Cadence as Early Indicators of Cognitive Impairment (Ding et al., 2025, JMIR) and Exploring Nightly Variability and Clinical Influences on Sleep Measures (Ding et al., 2025, Sleep Medicine). This work aims to lay the foundation for scalable, multimodal digital phenotyping approaches that can support early detection and continuous monitoring of cognitive decline in real-world settings.
What do you feel is most rewarding about your work, either as a professor or researcher?
What I find most rewarding about my work is the ability to contribute to research that drives real-world impact. It is deeply fulfilling to transform existing data into meaningful insights and to harness emerging digital tools to collect novel data. I also value the opportunity to collaborate with scholars around the world and to mentor students.