The Burn Medical Assistant: Developing Machine Learning Algorithms to Aid in the Estimation of Burn Wound Size (BURNMAN)

Abstract

The American Burn Association reports that roughly 450,000 patients receive hospital and emergency room treatment for burns each year, and of these patients, roughly 3,400 burn injury deaths occur. According to the Centers for Disease Control and Prevention (CDC), burns and fires are the third leading cause of death in the home. Thermal injuries occur in approximately 10% of combat trauma. Mortality rates for these patients remains high, half of casualties with 60-70% Total Body Surface Area (TBSA) burns die, whereas in civilian centers, roughly 50% of similarly matched patients with an 80% TBSA die. Since battlefield resources are inherently limited, triage is essential to determining the appropriate resources to be applied, and this is especially relevant to thermal injuries. It is critical for the medic on the battlefield to be able to make a rapid,accurate assessment of burn severity for triage, resuscitation, and evacuation planning purposes. But an error on the battlefield in estimating burn severity of over 10% can result in medics spending resources on unrecoverable patients at the expense of recoverable patients, or providing expectant care to a patient who could otherwise be saved.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2020
Accession Number
AD1105924

Entities

People

  • Maria L. Serio-melvin

Organizations

  • United States Army Institute of Surgical Research

Tags

Communities of Interest

  • Autonomy
  • C4I
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Body Regions
  • Burns
  • Cameras
  • Change Detection
  • Computer Vision
  • Computers
  • Contracts
  • Detection
  • Detectors
  • Health Services
  • Hospitals
  • Image Processing
  • Machine Learning
  • Medical Personnel
  • Neural Networks
  • Visible Spectra

Fields of Study

  • Medicine

Readers

  • Economics
  • Mathematics or Statistics
  • Trauma or Military Medicine

Technology Areas

  • AI & ML