Pre-Symptomatic Sepsis Detection Using a Wearable Biosensing System and Deep Learning Framework

Overview

Sepsis is one of the deadliest conditions in modern medicine, an extremely fatal cascading immune response to infection that kills more people each year than heart attacks and strokes combined, yet it remains notoriously difficult to detect before severe organ dysfunction develops. Every hour of delayed treatment increases the risk of death by nearly ten percent, and current hospital tools routinely fail to diagnose sepsis until symptoms have already escalated.  To address this, I built an early detection system using a custom wearable device and a deep learning model. The wearable continuously tracks vital signs, and the model analyzes the data to predict sepsis several hours before symptoms appear.  The system achieved over 98 percent accuracy in identifying at-risk patients, a performance that is significantly better than existing methods.  My project could help doctors act earlier, saving millions of lives annually, especially in resource-limited healthcare settings.

Awards (2)

• Bronze Medal
• Selected for CWSF 2026

Competition history

• CWSF 2026 Disease & Illness

Related projects

Closest projects by meaning, across every fair and year in the corpus.