DeepStroke+: a mobile AI app to quickly spot strokes in ambulances, ERs, and remote stroke consults

DeepStroke+: An Advanced Mobile AI Diagnostic Tool for Fast and Precise Detection of Acute Strokes in Mobile Stroke Units, Emergency Rooms, and Telestroke Triage

NIH-funded research Methodist Hospital Research Institute · NIH-11269162

This project will create and test an AI-powered app that uses short facial videos and speech samples to help emergency teams more quickly spot strokes in people with sudden neurological symptoms.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionMethodist Hospital Research Institute NIH-funded
Lab location1 site (Houston, United States)
Project IDNIH-11269162 on NIH RePORTER

What this research studies

From a patient perspective, researchers will ask English-speaking patients with possible stroke to describe a picture while a short facial video and audio are recorded. The team will train an AI called DeepStroke+ to recognize speech and facial patterns that suggest ischemic stroke, hemorrhage, or transient ischemic attack versus stroke mimics. The app will be deployed in mobile stroke units, emergency departments, and telestroke consultations and tested in those real-world triage situations. Study staff will compare the app’s triage suggestions to clinical diagnoses to measure how often strokes are correctly identified.

Who could benefit from this research

Good fit: Ideal candidates are English-speaking adults who present to a mobile stroke unit, emergency department, or telestroke service with sudden speech changes, facial droop, or other acute neurological symptoms and who can speak during the brief test.

Not a fit: Patients who cannot speak or produce the required speech sample (for example, those who are intubated, non-English speakers, or severely impaired) or whose stroke signs are not reflected in facial/speech changes may not benefit from the app.

Why it matters

Potential benefit: If successful, the app could help clinicians find strokes sooner, reduce missed diagnoses, and speed patients to the right treatments.

How similar studies have performed: Some prior clinical tools and AI approaches have aided stroke recognition, but using combined facial-video and speech AI in bedside and telestroke triage is relatively new and not yet widely proven.

Where this research is happening

Houston, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.