Related Experiment Video
Updated: Aug 28, 2025

08:16
High-Resolution Three-Dimensional Imaging of the Footpad Vasculature in a Murine Hindlimb Gangrene Model
Published on: March 16, 2022
3.6K
Classification Model for Diabetic Foot, Necrotizing Fasciitis, and Osteomyelitis
Jiye Kim1, Gilsung Yoo2, Taesic Lee3,4,5
1Department of Plastic Surgery, Yonsei University Wonju College of Medicine, Wonju 26411, Korea.
Biology
|September 23, 2022
Summary
This study developed classification models to aid in the early recognition of necrotizing fasciitis (NF) and osteomyelitis (OM) in diabetic foot ulcers (DFU). The models demonstrated strong predictive accuracy, potentially improving patient outcomes.
Area of Science:
- Medical Informatics
- Diabetology
- Infectious Diseases
Background:
- Diabetic foot ulcers (DFUs) present severe complications like necrotizing fasciitis (NF) and osteomyelitis (OM), increasing mortality and healthcare costs.
- Early detection of these complications is crucial for better clinical outcomes but remains challenging in standard clinical practice.
Purpose of the Study:
- To develop and validate classification models for identifying necrotizing fasciitis (NF) and osteomyelitis (OM) in patients with diabetic foot ulcers (DFU).
Main Methods:
- A multidisciplinary team curated features from literature and an automated platform.
- A dataset of 1581 patients (728 DFU, 76 NF, 777 OM) was split into training (70%) and validation (30%) sets.
- Classification models were trained and their performance evaluated using receiver operating characteristic (ROC) analysis.
Main Results:
- The NF classification model achieved an area under the ROC curve (AUC) of 0.80 in the validation set.
- The OM classification model achieved an AUC of 0.73 in the validation set.
- Both models demonstrated significant discriminatory power.
Conclusions:
- The developed classification models for NF and OM exhibit high accuracy and are easily applicable for patients with DFU.
- These models can assist clinicians in the early and accurate diagnosis of severe DFU complications.

