EUVIMEDEUVIMED entdecken
Crossref

Development of a Deep Learning‐Based Model for Pressure Injury Surface Assessment

Ankang Liu, Hualong Ma, Yanying Zhu, Qinyang Wu, Shihai Xu, Wei Feng, Haobin Liang, Jian Ma, Xinwei Wang, Xuemei Ye, Yanxiong Liu, Chao Wang und 3 weitere

Journal of Clinical Nursing · 2025

DOI: 10.1111/jocn.17645 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Nursing, 2025. Verfasst von Ankang Liu und 14 weiteren Autor:innen. Beteiligte Einrichtung: School of Nursing, Jinan University, Guangzhou, Guangdong, China. Hauptthemen laut MEDLINE: Pressure Ulcer, Deep Learning. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: Guangdong Nursing Association.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aim

To develop a deep learning‐based smart assessment model for pressure injury surface.

Design

Exploratory analysis study.

Methods

Pressure injury images from four Guangzhou hospitals were labelled and used to train a neural network model. Evaluation metrics included mean intersection over union (MIoU), pixel accuracy (PA), and accuracy. Model performance was tested by comparing wound number, maximum dimensions and area extent.

Results

From 1063 images, the model achieved 74% IoU, 88% PA and 83% accuracy for wound bed segmentation. Cohen's kappa coefficient for wound number was 0.810. Correlation coefficients were 0.900 for maximum length (mean difference 0.068 cm), 0.814 for maximum width (mean difference 0.108 cm) and 0.930 for regional extent (mean difference 0.527 cm 2 ).

Conclusion

The model demonstrated exceptional automated estimation capabilities, potentially serving as a crucial tool for informed decision‐making in wound assessment. Implications and Impact This study promotes precision nursing and equitable resource use. The AI‐based assessment model serves clinical work by assisting healthcare professionals in decision‐making and facilitating wound assessment resource sharing. Reporting Method The STROBE checklist guided study reporting. Patient or Public Contribution Patients provided image resources for model training.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pressure UlcerDeep LearningHumansChinaNeural Networks, ComputerMaleFemale

Stichwörter der Autor:innen

assessmentdeep learningimage segmentationneural networkpressure injury

Autor:innen und Institutionen

  • School of Nursing, Jinan University, Guangzhou, Guangdong, China.
  • Department of Continuing Care Services, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China.
  • Emergency Department, Shenzhen People's Hospital, Shenzhen, Guangdong, China.
  • College of Cyber Security, Jinan University, Guangzhou, Guangdong, China.
  • Burn and Wound Repair Center, Guangzhou Red Cross Hospital, Guangzhou, Guangdong, China.
  • Department of Burns, Plastic and Reconstructive Surgery and Wound Repair, Guangzhou First People's Hospital, Guangzhou, Guangdong, China.

ORCID-Profile: Qiaohong Yang

Förderung

  • Guangdong Nursing Association

Zitieren

APA

Liu, A., Ma, H., Zhu, Y., Wu, Q., Xu, S., Feng, W., Liang, H., Ma, J., Wang, X., Ye, X., Liu, Y., Wang, C., Sun, X., Xiang, S., & Yang, Q. (2025). Development of a Deep Learning‐Based Model for Pressure Injury Surface Assessment. Journal of Clinical Nursing. https://doi.org/10.1111/jocn.17645

Vancouver

Liu A, Ma H, Zhu Y, Wu Q, Xu S, Feng W, et al. Development of a Deep Learning‐Based Model for Pressure Injury Surface Assessment. Journal of Clinical Nursing. 2025. doi:10.1111/jocn.17645

BibTeX
@article{Liu2025,
  author = {Liu, Ankang and Ma, Hualong and Zhu, Yanying and Wu, Qinyang and Xu, Shihai and Feng, Wei and Liang, Haobin and Ma, Jian and Wang, Xinwei and Ye, Xuemei and Liu, Yanxiong and Wang, Chao and Sun, Xu and Xiang, Shijun and Yang, Qiaohong},
  title = {Development of a Deep Learning‐Based Model for Pressure Injury Surface Assessment},
  journal = {Journal of Clinical Nursing},
  year = {2025},
  doi = {10.1111/jocn.17645}
}
Kostenlos starten →