DL4Burn: Burn Surgical Candidacy Prediction using Multimodal Deep Learning.

Journal: AMIA ... Annual Symposium proceedings. AMIA Symposium
Published Date: Jan 1, 2021

Abstract

Burn wounds are most commonly evaluated through visual inspection to determine surgical candidacy, taking into account burn depth and individualized patient factors. This process, though cost effective, is subjective and varies by provider experience. Deep learning models can assist in burn wound surgical candidacy with predictions based on the wound and patient characteristics. To this end, we present a multimodal deep learning approach and a complementary mobile application - DL4Burn - for predicting burn surgical candidacy, to emulate the multi-factored approach used by clinicians. Specifically, we propose a ResNet50-based multimodal model and validate it using retrospectively obtained patient burn images, demographic, and injury data.

Authors

  • Sirisha Rambhatla
    Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A.
  • Samantha Huang
    Keck School of Medicine, University of Southern California, Los Angeles, CA, U.S.A.
  • Loc Trinh
    Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A.
  • Mengfei Zhang
    Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A.
  • Boyuan Long
    Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A.
  • Mingtao Dong
    Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A.
  • Vyom Unadkat
    Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A.
  • Haig A Yenikomshian
    Southern California Regional Burn Center at LAC+USC, University of Southern California, Los Angeles, CA.
  • Justin Gillenwater
    Southern California Regional Burn Center at LAC+USC, University of Southern California, Los Angeles, CA.
  • Yan Liu
    Department of Clinical Microbiology, Shanghai Tenth People's Hospital, School of Medicine, Tongji University, Shanghai, 200072, People's Republic of China.

Keywords

External Resources

Popular Topics
Recent Journals