Clinical Investigation of a Rapid Non-invasive Multispectral Imaging Device Utilizing an Artificial Intelligence Algorithm for Improved Burn Assessment
Journal of Burn Care & Research · 2023
DOI: 10.1093/jbcr/irad051 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Burn Care & Research, 2023. Verfasst von Jeffrey E Thatcher und 7 weiteren Autor:innen. Beteiligte Einrichtung: Spectral MD, Inc., Dallas, TX, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Burns. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Biomedical Advanced Research and Development Authority.
Abstract (Originalsprache)
Currently, the incorrect judgment of burn depth remains common even among experienced surgeons. Contributing to this problem are change in burn appearance throughout the first week requiring periodic evaluation until a confident diagnosis can be made. To overcome these issues, we investigated the feasibility of an artificial intelligence algorithm trained with multispectral images of burn injuries to predict burn depth rapidly and accurately, including burns of indeterminate depth. In a feasibility study, 406 multispectral images of burns were collected within 72 hours of injury and then serially for up to 7 days. Simultaneously, the subject’s clinician indicated whether the burn was of indeterminate depth. The final depth of burned regions within images were agreed upon by a panel of burn practitioners using biopsies and 21-day healing assessments as reference standards. We compared three convolutional neural network architectures and an ensemble in their capability to automatically highlight areas of nonhealing burn regions within images. The top algorithm was the ensemble with 81% sensitivity, 100% specificity, and 97% positive predictive value (PPV). Its sensitivity and PPV were found to increase in a sigmoid shape during the first week postburn, with the inflection point at day 2.5. Additionally, when burns were labeled as indeterminate, the algorithm’s sensitivity, specificity, PPV, and negative predictive value were: 70%, 100%, 97%, and 100%. These results suggest multispectral imaging combined with artificial intelligence is feasible for detecting nonhealing burn tissue and could play an important role in aiding the earlier diagnosis of indeterminate burns.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Spectral MD, Inc., Dallas, TX, USA.
- Baylor Scott and White, The Heart Hospital, Baylor Scott and White Research Institute, Dallas, TX, USA.
- Atrium Health Wake Forest Baptist Medical Center Burn Center, Winston-Salem, NC, USA.
- The Burn Center at University Medical Center New Orleans, LA, USA.
ORCID-Profile: Faliu Yi
Förderung
- Biomedical Advanced Research and Development Authority
Zitieren
APA
Thatcher, J. E., Yi, F., Nussbaum, A. E., DiMaio, J. M., Dwight, J., Plant, K., Carter, J. E., & Holmes, J. H. (2023). Clinical Investigation of a Rapid Non-invasive Multispectral Imaging Device Utilizing an Artificial Intelligence Algorithm for Improved Burn Assessment. Journal of Burn Care & Research. https://doi.org/10.1093/jbcr/irad051
Vancouver
Thatcher JE, Yi F, Nussbaum AE, DiMaio JM, Dwight J, Plant K, et al. Clinical Investigation of a Rapid Non-invasive Multispectral Imaging Device Utilizing an Artificial Intelligence Algorithm for Improved Burn Assessment. Journal of Burn Care & Research. 2023. doi:10.1093/jbcr/irad051
BibTeX
@article{Thatcher2023,
author = {Thatcher, Jeffrey E and Yi, Faliu and Nussbaum, Amy E and DiMaio, John Michael and Dwight, Jason and Plant, Kevin and Carter, Jeffrey E and Holmes, James H},
title = {Clinical Investigation of a Rapid Non-invasive Multispectral Imaging Device Utilizing an Artificial Intelligence Algorithm for Improved Burn Assessment},
journal = {Journal of Burn Care & Research},
year = {2023},
doi = {10.1093/jbcr/irad051}
}
EUVIMED