Related Experiment Video
Updated: May 29, 2026
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Research on real-time detection and staging technology for pressure injuries in critically ill patients based on the
Fengbo Guo1, Ningbo Cao1, Jingyi Nie1
1Shanxi Provincial People's Hospital, Taiyuan, Shanxi, China.
Background:
Aiming to address the clinical challenges of high incidence rates of pressure injuries (PIs) in critically ill patients and the subjectivity and inefficiency of traditional assessment methods, this study developed a real-time detection and staging technology based on the YOLOv8 deep learning model. This technology enables rapid and objective staging of PIs, aiming to overcome the limitations of current manual assessments and provide support for precision nursing care.
Objective:
To develop and validate a real-time detection and staging system for PIs using the YOLOv8 deep learning model.
Study Design:
A total of 507 PI images from intensive care unit patients (Jan 2023-Jun 2025) were randomly divided into training (414) and test (93) sets at an 8:2 ratio. Images were classified into six stages per NPUAP guidelines. Five YOLOv8 versions were developed using transfer learning, with AdamW optimizer and dynamic learning rate adjustment. The best model was evaluated on accuracy, mean average precision (mAP), and inference speed.
Results:
This model effectively enhanced the objectivity and accuracy of pressure injury (PI) staging identification. In testing with 93 PI images, YOLOv8l achieved an overall accuracy of 96.8% and a mAP@50 of 0.847, while maintaining an inference speed of 28.6 FPS (frames per second)-outperforming other versions. Additionally, the model demonstrated high prediction accuracy across all six PI stages: all Stage 2, Stage 4, and Unstageable images were correctly predicted; one image each in Stage 1, Stage 3, and Deep Tissue Injury (DTI) was misclassified.
Conclusions:
For PI staging identification, the PI assessment system built on the YOLOv8l deep learning model demonstrates high accuracy and efficiency, providing reliable support for clinical decision-making.
Relevance To Clinical Practice:
This system enables objective PI evaluation and personalized care planning, which may reduce PI-related complications and associated healthcare costs.
