AI Platform Lets Patients Chat With Their Medical Devices in Real Time

Researchers at the University of Pennsylvania have built an AI-driven platform that lets people exchange messages with their medical devices through a smartphone app and receive feedback in real time. A proof-of-concept study in patients monitored for seizures was published in Nature Medicine.
- Penn researchers built an AI platform that lets patients message their medical devices via a smartphone app and get real-time feedback.
- The proof-of-concept study involved participants undergoing monitoring for seizures and was published in Nature Medicine.
- Participants could ask about brain activity, receive personalized alerts, report symptoms and behaviors, and help train the system.
- Senior author Brian Litt says the device and patient can learn together over time.
How the platform works
The system was tested with participants who were undergoing monitoring for seizures. Through a smartphone application, they could send messages to their device and get responses as events unfolded.
According to the Penn team, participants could ask questions about their brain activity, receive personalized alerts, and report symptoms and behaviors. They could also help train the system to better recognize seizure-related patterns.
The work comes from researchers at the Perelman School of Medicine and the Center for Neuroengineering and Therapeutics (CNT) at the University of Pennsylvania. The findings were published in Nature Medicine.
From passive data collection to collaboration
The researchers describe the platform as a fundamental shift from today's medical devices. Most current devices largely collect data that clinicians review periodically. The new approach instead aims for systems that actively collaborate with patients to manage their health.
Senior author Brian Litt, MD, a professor of Neurology, Neurosurgery, and Bioengineering, put the idea this way: "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."
He added a second point about learning on both sides: "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."
What it means
The study is described as a proof of concept, so the results show feasibility in a seizure-monitoring setting rather than a finished clinical product. The source does not give details on sample size, performance figures, regulatory status or availability.
If the approach holds up in further work, patients could get immediate alerts about changes detected by their device instead of waiting for periodic review by a specialist. The two-way exchange could also let patients contribute information that helps the system recognize patterns that matter to them. The researchers frame this as a path toward devices that learn alongside the people who use them.
Penn Engineering: AI Platform Allows Real-Time Conversation Between Patients and their Medical Devices
