Indian American Student Develops App for Early Stroke Detection

Written on 04/02/2025
Muzaina Fathima


Image Credit: news.berkeley.edu

Berkeley, California: In a groundbreaking move, UC Berkeley undergraduate Ashmita Kumar has developed "Code Blue," an AI-powered application designed to detect early signs of strokes using everyday devices like smartphones and computers.

Inspired by personal family experiences, Kumar's innovation seeks to alert users and emergency services promptly, potentially reducing the devastating effects of delayed stroke treatment.​

Key Facts:

  • Ashmita Kumar is a third-year electrical engineering and computer sciences student at UC Berkeley.​

 

  • Technology: Utilizes AI to monitor speech and facial expressions via device cameras and microphones.​

 

  • Pilot Testing: Collaborating with UC San Francisco doctors to test with an initial group of five patients, with plans to expand to 100 participants.​

Kumar's journey began at age eight when her grandfather suffered a severe stroke after failing to recognize early symptoms.

This personal experience, coupled with a similar scare involving her father in 2021, ignited her determination to leverage technology for early stroke detection.

"Everybody has devices now, especially after COVID, and telehealth has taken off," Kumar noted. "So why don’t we use that as a way to make sure that people, when they experience a stroke, can use those existing devices to get treatment when they need it?" ​

Code Blue operates discreetly in the background, analyzing users' speech and facial movements every 30 seconds for indicators like slurred speech or facial asymmetry.

If potential stroke symptoms are detected, the app alerts the user and can notify emergency services, ensuring timely medical intervention.

To protect privacy, the system analyzes data in real-time without storing images or audio. ​

The broader implications of Code Blue are significant, especially considering that over 795,000 people in the U.S. experience strokes annually, with someone dying from a stroke every three minutes.

Early detection and prompt treatment can substantially reduce long-term disabilities.

Looking ahead, Kumar aims to obtain FDA approval for Code Blue, facilitating widespread adoption similar to other health-monitoring technologies like the Apple Watch.

She continues to refine the app, emphasizing user privacy and accuracy, and plans to expand testing to a larger patient group.

Do You Know?

The term "Code Blue" is commonly used in hospitals to indicate a medical emergency requiring immediate resuscitation efforts.

Kumar's choice of this name underscores the urgency of timely stroke detection and intervention.​

Key Terms:

AI (Artificial Intelligence): Simulation of human intelligence in machines programmed to think and learn.​

Facial Asymmetry: Uneven appearance of the face, which can be a sign of neurological events like strokes.​

Telehealth: The delivery of health-related services and information via electronic and telecommunication technologies.