A new AI-driven platform developed at the University of Pennsylvania lets people interact with their medical devices through a smartphone app, sending messages and receiving feedback in real time. In a proof-of-concept study of patients being monitored for seizures, published October 13, 2026 in Nature Medicine, participants could ask questions about their brain activity, receive personalized alerts, report symptoms and behaviors, and help train the system to better recognize seizure-related patterns.
The research, from the Perelman School of Medicine and Penn’s Center for Neuroengineering and Therapeutics (CNT), points to a shift from today’s medical devices, which largely collect data for clinicians to review periodically, toward systems that actively collaborate with patients to manage their health.
“The idea is that instead of waiting for a specialist to analyze the data collected by your device, the device could detect changes and alert you immediately, like your own personal Jiminy Cricket on your shoulder,” said senior author Brian Litt, MD, a professor of Neurology, Neurosurgery, and Bioengineering. “More importantly, both the patient and the device can learn together over time. The device learns what matters to the patient, and the patient learns how their behavior affects their health.”
Turning Data Into Conversations
The study enrolled 13 adults undergoing continuous electroencephalogram (EEG) brain monitoring in Penn’s Epilepsy Monitoring Unit, for reasons including locating the source of their seizures or pre-surgical evaluation. They tested a platform built by Penn Bioengineering PhD students led by Zack Goldblum, Haoer Shi, and Zhongchuan Xu, with three components:
- Data capture: software that continuously captured EEG data from electrodes in the participant’s brain.
- Cloud analysis: a secure, HIPAA-compliant cloud environment that analyzed incoming data in near real time.
- Conversational app: a smartphone app featuring a Penn-developed, AI-powered conversational agent.
Through the app, patients could ask about their brain activity, request visualizations of trends, report symptoms, and receive alerts or surveys. The device could also contact patients when it detected changes of interest and learn “on the fly” from their responses. Researchers analyzed 1,307 messages exchanged during the study, most of them about seizure events, sleep, mood, energy levels, and other factors that can influence seizure activity.
Several participants said the platform helped explain patterns they had noticed but struggled to understand. One said the system helped “solidify what I felt to be true between some of my episodes and emotions.”
Learning Together
Patients could also teach the system, flagging which seizures it identified correctly and which were false alarms, which substantially improved its accuracy. Clinicians could review the program’s assessments and add their own annotations through an “expert in the loop” algorithm designed to limit expert input to high-value cases. As the systems become more personalized, researchers believe they will need only rare clinical supervision, making them practical for long-term outpatient use.
Beyond Epilepsy
The team sees broad potential for cardiac devices, insulin pumps, and emerging treatments for neuropsychiatric conditions such as Parkinson’s disease, depression, obsessive-compulsive disorder, addiction, and cognitive disorders. It is already preparing studies with Lauren Hammer, MD, PhD, an assistant professor of Neurology and Bioengineering, to apply the platform to automatically tune deep brain stimulation devices for Parkinson’s disease. Other work is incorporating wearables for insomnia, epilepsy, and brain and vital-sign monitoring.
“Patients often understand aspects of their disease that sensors cannot measure directly,” Litt said. “Imagine an insulin pump that can answer questions about how a meal will affect blood sugar, or a Parkinson’s device that adjusts treatment based on how a patient feels during a walk or writing a letter. We envision medical devices becoming partners in care that learn alongside patients and help them make better decisions every day.”
The work is supported by a $5.6 million NIH Pioneer Award (DP1 NS122038-01) and builds on Litt’s broader effort to develop a new generation of brain-computer interfaces that sense physiologic signals, communicate with patients, and adapt treatment in real time. Ongoing research will evaluate whether the platform can reduce seizure frequency and severity, improve quality of life, and lower emergency visits and health care use, with plans to expand into outpatient settings using minimally invasive EEG and wearable technologies.
