DL4Burn: Burn Surgical Candidacy Prediction using Multimodal Deep Learning.

Autor:	Rambhatla S; Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A., Huang S; Keck School of Medicine, University of Southern California, Los Angeles, CA, U.S.A., Trinh L; Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A., Zhang M; Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A., Long B; Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A., Dong M; Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A., Unadkat V; Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A., Yenikomshian HA; Southern California Regional Burn Center at LAC+USC, University of Southern California, Los Angeles, CA., Gillenwater J; Southern California Regional Burn Center at LAC+USC, University of Southern California, Los Angeles, CA., Liu Y; Computer Science Department, University of Southern California, Los Angeles, CA, U.S.A.
Jazyk:	angličtina
Zdroj:	AMIA ... Annual Symposium proceedings. AMIA Symposium [AMIA Annu Symp Proc] 2022 Feb 21; Vol. 2021, pp. 1039-1048. Date of Electronic Publication: 2022 Feb 21 (Print Publication: 2021).
Abstrakt:	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. (©2021 AMIA - All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu