Development of a Pressure Ulcer Stage Determination System for Community Healthcare Providers Using a Vision Transformer Deep Learning Model

Overview

Journal Medicine (Baltimore)

Specialty General Medicine

Date 2025 Feb 17

PMID 39960905

Authors

Young-Bok Cho

Hana Yoo

Affiliations

Soon will be listed here.

Abstract

This study reports the first steps toward establishing a computer vision system to help caregivers of bedridden patients detect pressure ulcers (PUs) early. While many previous studies have focused on using convolutional neural networks (CNNs) to elevate stages, hardware constraints have presented challenges related to model training and overreliance on medical opinions. This study aimed to develop a tool to classify PU stages using a Vision Transformer model to process actual PU photos. To do so, we used a retrospective observational design involving the analysis of 395 images of different PU stages that were accurately labeled by nursing specialists and doctors from 3 hospitals. In the pressure ulcer cluster vision transformer (PUC-ViT) model classifies the PU stage with a mean ROC curve value of 0.936, indicating a model accuracy of 97.76% and F1 score of 95.46%. We found that a PUC-ViT model showed higher accuracy than conventional models incorporating CNNs, and both effectively reduced computational complexity and achieved low floating point operations per second. Furthermore, we used internet of things technologies to propose a model that allows anyone to analyze input images even at low computing power. Based on the high accuracy of our proposed model, we confirm that it enables community caregivers to detect PUs early, facilitating medical referral.

References

Qu C, Luo W, Zeng Z, Lin X, Gong X, Wang X . The predictive effect of different machine learning algorithms for pressure injuries in hospitalized patients: A network meta-analyses. Heliyon. 2022; 8(11):e11361. PMC: 9649958. DOI: 10.1016/j.heliyon.2022.e11361. View

Aldughayfiq B, Ashfaq F, Jhanjhi N, Humayun M . YOLO-Based Deep Learning Model for Pressure Ulcer Detection and Classification. Healthcare (Basel). 2023; 11(9). PMC: 10178524. DOI: 10.3390/healthcare11091222. View

Kim M, Kim T, Kim D, Lee D, Kim D, Heo J . In-Advance Prediction of Pressure Ulcers via Deep-Learning-Based Robust Missing Value Imputation on Real-Time Intensive Care Variables. J Clin Med. 2024; 13(1). PMC: 10780209. DOI: 10.3390/jcm13010036. View

Dweekat O, Lam S, McGrath L . Machine Learning Techniques, Applications, and Potential Future Opportunities in Pressure Injuries (Bedsores) Management: A Systematic Review. Int J Environ Res Public Health. 2023; 20(1). PMC: 9819814. DOI: 10.3390/ijerph20010796. View

Paolini G, Sorotos M, Firmani G, Gravili G, Ceci D, Santanelli di Pompeo F . Low-vacuum negative pressure wound therapy protocol for complex wounds with exposed vessels. J Wound Care. 2022; 31(1):78-85. DOI: 10.12968/jowc.2022.31.1.78. View

Gallagher P, Barry P, Hartigan I, McCluskey P, OConnor K, OConnor M . Prevalence of pressure ulcers in three university teaching hospitals in Ireland. J Tissue Viability. 2008; 17(4):103-9. DOI: 10.1016/j.jtv.2007.12.001. View

Fulbrook P, Miles S, Coyer F . Prevalence of pressure injury in adults presenting to the emergency department by ambulance. Aust Crit Care. 2018; 32(6):509-514. DOI: 10.1016/j.aucc.2018.10.002. View

Sin P, Hokynkova A, Marie N, Andrea P, Krc R, Podrouzek J . Machine Learning-Based Pressure Ulcer Prediction in Modular Critical Care Data. Diagnostics (Basel). 2022; 12(4). PMC: 9030498. DOI: 10.3390/diagnostics12040850. View

Zhao Z, Zeng Z, Xu K, Chen C, Guan C . DSAL: Deeply Supervised Active Learning From Strong and Weak Labelers for Biomedical Image Segmentation. IEEE J Biomed Health Inform. 2021; 25(10):3744-3751. DOI: 10.1109/JBHI.2021.3052320. View

10.

Walther F, Heinrich L, Schmitt J, Eberlein-Gonska M, Roessler M . Prediction of inpatient pressure ulcers based on routine healthcare data using machine learning methodology. Sci Rep. 2022; 12(1):5044. PMC: 8943147. DOI: 10.1038/s41598-022-09050-x. View

11.

Kim G, Park M, Kim K . The Effect of Pressure Injury Training for Nurses: A Systematic Review and Meta-analysis. Adv Skin Wound Care. 2020; 33(3):1-11. DOI: 10.1097/01.ASW.0000653164.21235.27. View

12.

Xu Z, Wang Y, Lu D, Yu L, Yan J, Luo J . All-Around Real Label Supervision: Cyclic Prototype Consistency Learning for Semi-Supervised Medical Image Segmentation. IEEE J Biomed Health Inform. 2022; 26(7):3174-3184. DOI: 10.1109/JBHI.2022.3162043. View

13.

Pei J, Guo X, Tao H, Wei Y, Zhang H, Ma Y . Machine learning-based prediction models for pressure injury: A systematic review and meta-analysis. Int Wound J. 2023; 20(10):4328-4339. PMC: 10681397. DOI: 10.1111/iwj.14280. View

14.

Capon A, Pavoni N, Mastromattei A, Di Lallo D . Pressure ulcer risk in long-term units: prevalence and associated factors. J Adv Nurs. 2007; 58(3):263-72. DOI: 10.1111/j.1365-2648.2007.04232.x. View

15.

Liu T, Christian M, Chu Y, Chen Y, Chang C, Lai F . A pressure ulcers assessment system for diagnosis and decision making using convolutional neural networks. J Formos Med Assoc. 2022; 121(11):2227-2236. DOI: 10.1016/j.jfma.2022.04.010. View