MIT researchers will lead PYTHIA, a four-year project with up to $38 million in funding from the Advanced Research Projects Agency for Health (ARPA-H), to develop a noninvasive wearable patch for continuous monitoring of heart disease and sepsis biomarkers. The name PYTHIA stands for “predictive platform for physiological and therapeutic health intervention and adaptive management.” The project plan calls for the patch to capture clinical-grade health information in real time and draw power from the patient’s body heat; the information could help clinicians identify heart failure and sepsis before irreversible damage occurs. Researchers also believe the minimally invasive device could track recovery after hospital discharge and help clinicians develop more effective treatments.
The project targets conditions with a substantial public-health toll: the article cites Centers for Disease Control and Prevention figures identifying heart disease as the leading cause of death in the United States and reporting that sepsis kills at least 350,000 U.S. adults each year and is the leading cause of death in hospitals. Principal investigator Ahmad Bahai says the team chose the diseases because they are highly lethal and biomarker detection could improve diagnosis and treatment. Bahai is a professor of the practice in MIT’s Department of Electrical Engineering and Computer Science and a member of its Research Laboratory of Electronics. MIT researchers Joel Voldman, Tim Swager, Hadley Sikes, and Collin Stultz will join Bahai on the project; their stated professorial appointments are in electrical engineering and computer science, chemistry, and chemical engineering.
Bahai describes the effort as an MIT-centered research-and-development ecosystem intended to help translate research into a device usable in a clinic, and says the project aims to affect the future of personalized health care.
PYTHIA grew out of MIT’s Program for Health Sciences and Semiconductors, which Bahai co-founded. The program applies advances in semiconductor technology and nanotechnology to diagnostics, therapeutics, and drug discovery. Bahai researches electrochemical devices, optics, magnetics, and ultrasonics in his “Waves, Bites, and Molecules” lab; his group aims to develop clinical-grade wearables for continuous biomarker tracking and real-time intervention. Earlier work on continuous glucose monitors inspired Bahai and colleagues to consider using semiconductor technology to track other biomarkers, leading to PYTHIA’s launch.
The proposed chip-based patch would measure heart-failure and sepsis biomarkers in interstitial fluid beneath the skin. The target molecules are difficult to detect because they occur at very low concentrations. The planned system would use a chemical reaction to bind chemicals to the biomarker molecules, making them easier to identify, while microelectronics would measure them at sensitivity intended for clinical applications. Because continuous measurements would generate large volumes of data, PYTHIA is planned to use on-chip AI models to turn raw measurements into information for clinicians. Bahai likens the automatic monitoring to a blood test every 15 minutes or so; this is an analogy, not a reported test of the device or a specified sampling interval.
The team plans to develop and test electronic components for a small, low-power chip, then take the wearable through preclinical and clinical trials toward commercial-scale manufacture. The patch is still a proposed system, not a demonstrated clinical monitor. Bahai says clinical and industry collaborators contribute experience with practical constraints, regulation, and clinical need, and describes the possible health impact as potential rather than established. ARPA-H funds PYTHIA through its Delphi Program, led by Program Manager Leonard Tender. Delphi teams apply microelectronics to biosensing and aim to develop devices that safely, securely, and continuously monitor internal health signals. The project is supported under ARPA-H agreement AY2AX000243; the announcement says its contents do not necessarily represent the agency’s official views.