In her captivating TEDxMIT talk, “Could AI Predict Disease Risk From Sleep Data?”, Dina Katabi explores the groundbreaking intersection of artificial intelligence and healthcare. Katabi discusses how innovative technology can analyze sleep patterns to identify early signs of various diseases. By leveraging advanced machine learning techniques, her research harnesses the vast amount of data generated during sleep to uncover hidden health indicators that traditional methods might miss.
With a focus on conditions such as diabetes and cardiovascular diseases, Katabi underscores the potential of AI to transform preventive healthcare. She presents compelling evidence of how accurately monitoring sleep can lead to better risk assessments, ultimately empowering individuals to take proactive steps towards their health. Her insights suggest a future where personalized medicine becomes a reality, driven by data-driven predictions that enhance our understanding of wellness. This thought-provoking presentation invites viewers to consider the significant roles that technology and science can play in reshaping healthcare and improving lives through informed, predictive analytics.
Watch the video by TEDxTalks
Author Video Description
NOTE FROM TED: Research discussed in this talk remains an ongoing field of study and warrants further peer review. TEDx events are independently organized by volunteers. The guidelines we give TEDx organizers are described in more detail here: http://storage.ted.com/tedx/manuals/tedx_content_guidelines.pdf
What if a single night of sleep could reveal your future health?
MIT professor Dina Katabi introduces a groundbreaking AI system that can predict disease risk and identify medication use using only wireless signals captured while you sleep—without wearables, cameras, or electrodes. By combining contact-free sensing with a powerful AI foundation model, her team has shown that sleep contains an extraordinary amount of information about the body’s neurological, respiratory, cardiovascular, and metabolic health.
From detecting Alzheimer’s disease, Parkinson’s disease, stroke risk, and diabetes to identifying medications like antidepressants and insulin, this technology has the potential to transform preventive medicine. Katabi explains how AI learns hidden relationships between breathing and brain activity, opening the door to a future where healthcare becomes continuous, passive, and deeply personalized. Dina Katabi received a B.S. (1995) from Damascus University and an M.S. (1999) and Ph.D. (2003) from the Massachusetts Institute of Technology. She joined the faculty of MIT in 2003, where she is currently a professor in the Department of Electrical Engineering and Computer Science, director of the MIT Center for Wireless Networks and Mobile Computing (Wireless@MIT), and a member of the Computer Science and Artificial Intelligence Laboratory, where she leads the Networks at MIT group (NETMIT). This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at https://www.ted.com/tedx
About TEDxTalks
TEDx is an international community that organizes TED-style events anywhere and everywhere — celebrating locally-driven ideas and elevating them to a global stage. TEDx events are produced independently of TED conferences, each event curates speakers on their own, but based on TED’s format and rules.
Video “Could AI Predict Disease Risk From Sleep Data? | Dina Katabi | TEDxMIT” was uploaded on 08/07/2026 to Youtube Channel TEDx Talks