Intelligent Health Monitoring in the Home

ABSTRACT

Delivering healthcare to patients in their homes is the future of healthcare, as it offers better access to healthcare for individuals living in remote areas, far away from hospitals and clinics. With a global aging population, chronic diseases are on the rise, making continuous monitoring of patients in their homes crucial for early detection and prevention of complications that may require hospitalization. Moreover, providing healthcare at home is cost-effective, as it reduces the need for hospitalization and the associated costs. Advances in machine learning and health sensors have begun to transform in-home healthcare. However, incorporating these technologies into clinical applications for in-home use must overcome challenges such as simplifying compliance, ensuring that the data quality is comparable to the medical gold standard, and preserving data privacy.

In this talk, I will showcase three projects that provide data-driven machine learning models for home-based healthcare applications that address all these challenges. Firstly, I will present the first AI-powered digital biomarker for Parkinson’s Disease that can detect the disease, estimate its severity, and track its progression using nocturnal breathing data. This biomarker is objective, non-invasive, sensitive, and can be used for at-home assessments. Secondly, I will discuss the first work that enables contactless monitoring of blood oxygen saturation in patients' homes using wireless signals. This technology can passively monitor blood oxygen levels, which is especially important for elderly individuals who are susceptible to fluctuations in oxygen levels, particularly during sleep. Lastly, I will present a model designed to capture the daily-life activities of elderly individuals who may be experiencing conditions such as Alzheimer's or dementia. It enables clinicians and caregivers to remotely monitor health-related conditions, allowing them to provide care when needed.

SPEAKER BIO

Yuan Yuan is a Postdoc Associate at the Computer Science & Artificial Intelligence Lab (CSAIL) of MIT, working with Dina Katabi. She is also affiliated with Brigham and Women’s Hospital (BWH), Harvard Medical School. She received her Ph.D. degree from the Hong Kong University of Science and Technology, advised by Dit-Yan Yeung. She has been a visiting research scholar at the Robotics Institute of Carnegie Mellon University. Yuan’s research interests lie in the fields of machine learning, computer vision, AI for healthcare, and medical AI, specifically on contactless health monitoring and developing digital biomarkers for neurological diseases with machine learning. Her research has appeared in top-tier journals and conferences including Nature Medicine, NeurIPS, ICLR, CVPR, ICCV, ECCV, etc. Her work has received widespread media coverage from outlets such as Forbes, The Washington Post, BBC, etc. Her work on a AI-powered biomarker for Parkinson's disease has been recognized as one of the ten breakthroughs and critical developments in Nature Medicine's Notable Advances 2022.