RESUMO
Significance: Over the past decade, machine learning (ML) algorithms have rapidly become much more widespread for numerous biomedical applications, including the diagnosis and categorization of disease and injury. Aim: Here, we seek to characterize the recent growth of ML techniques that use imaging data to classify burn wound severity and report on the accuracies of different approaches. Approach: To this end, we present a comprehensive literature review of preclinical and clinical studies using ML techniques to classify the severity of burn wounds. Results: The majority of these reports used digital color photographs as input data to the classification algorithms, but recently there has been an increasing prevalence of the use of ML approaches using input data from more advanced optical imaging modalities (e.g., multispectral and hyperspectral imaging, optical coherence tomography), in addition to multimodal techniques. The classification accuracy of the different methods is reported; it typically ranges from â¼70% to 90% relative to the current gold standard of clinical judgment. Conclusions: The field would benefit from systematic analysis of the effects of different input data modalities, training/testing sets, and ML classifiers on the reported accuracy. Despite this current limitation, ML-based algorithms show significant promise for assisting in objectively classifying burn wound severity.
Assuntos
Queimaduras , Pele , Humanos , Imagem Óptica/métodos , Aprendizado de Máquina , Algoritmos , Queimaduras/diagnóstico por imagemRESUMO
The current system of burn care delivery attempts to meet the needs of the nearly 500 000 patients in the United States who require medical treatment annually. However, specialization of care and lack of fundamental burn and wound care knowledge among graduating medical trainees has unintended consequences, leaving the system inefficient, with inherent inequities in care delivery and with the potential to be overwhelmed in a mass casualty event. While increasing accessibility to specialty burn centers through technology could mitigate some of these problems, increased education is more practical. The implementation of a formal wound care curriculum in medical school would address the problems associated with chronic wounds in the United States. Additionally, this curriculum would be a natural extension of exposure to the basics of burn care, a relevant skill set in any specialty.