Skip to main navigation Skip to search Skip to main content

I-Corps: Translation Potential of a Diagnostic Decision Support System for Real-Time Detection of Life-threatening Brain Injury States

Project: Research

Abstract & Details

Description

Award ID: 2536428

This I-Corps project investigates the commercial potential of brain monitoring software for novice-level stroke recognition in anesthetized patients. Approximately 35,000 anesthetized patients each year in the United States suffer a stroke during a medical procedure. Because such patients are unable to manifest symptoms of stroke, the physician is not alerted, and the stroke is subsequently left untreated. Untreated stroke in this setting results in unexpected and premature death, physical and cognitive disability, and great hardship to these patients and their families. Additionally, the total cost of these strokes is about $2.8 billion per year. Brain electrical activity monitoring during anesthesia would enable real-time stroke detection, but it requires continuous high-level-expert interpretation. The need for expert interpretation prevents the large-scale use of brain electrical monitoring for stroke. Software to enable novice-level brain monitoring during anesthesia removes the need for an expert interpreter and expands the use of brain wave monitoring. With its use, the physician is alerted to the presence of stroke the moment it occurs. By having the stroke recognized immediately, the patient can receive emergency treatment to relieve the cause of stroke. By quickly reversing the stroke, the patients will be spared the severe consequences of stroke including potential emotional hardship, disability, and death. This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. This solution is based on the development of the Correlate Of Injury to the Nervous System index calculated from electroencephalographic brain recordings. The index is a method of summarizing brain electrical activity from multiple sensors on the scalp into a single number that is calculated every 4 seconds. The number which ranges from 0 to 100 indicates whether there is an area of brain that has impaired electrical activity resulting from stroke. Like a pulse-oximeter (which is used to measure blood-oxygen content), index values between 90-100 are interpreted as normal, indicating a healthy brain without stroke. As the index decreases into values below 90, the clinician recognizes the potential presence of stroke. As values progressively decrease, the likelihood of stroke increases, such that a value below 70 almost certainly indicates the presence of life-threatening stroke. Additionally, the index generates a visualization which displays the area of brain affected by stroke. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Ruth Shuman
StatusActive
Effective start/end date09/15/2508/31/26

Funding

  • I-Corps Teams: $50,000.00

Active Fiscal Year

  • FY2026
  • FY2025

Start Fiscal Year

  • FY2025

TIP Programs

  • I-Corps Teams

Key Technology Areas

  • Artificial Intelligence
  • (confidence score: 99%)
  • Biotechnology
  • (confidence score: 100%)

Technology Foci

  • Medical Technology
  • (confidence score: 100%)
  • Artificial Intelligence (Broad)
  • (confidence score: 100%)

Congressional District at Award

  • District n. 11 of California

Current Congressional District

  • District n. 11 of California

United States

  • California

Core Based Statistical Area (CBSA)

  • San Francisco-Oakland-Fremont, CA

County

  • County: San Francisco, CA

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint. Learn more about Elsevier's Fingerprint Engine here: https://beta.elsevier.com/products/elsevier-fingerprint-engine