Related Experiment Video
Updated: May 1, 2026
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Explainable machine learning differentiates necrotizing fasciitis and osteomyelitis via routine blood biomarkers
Parhat Yasin1, Zubaidanmu Aizezi2, Shiming Dong3
1Department of Spine Surgery, The Sixth Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, PR China.
Abstract:
Necrotizing fasciitis (NF) and osteomyelitis (OM) are severe, limb-threatening infections with overlapping features, making early differentiation challenging. To address this, we developed and validated an explainable machine learning model using routine blood biomarkers from a retrospective, multi-center cohort of 3415 patients (579 NF, 2836 OM). Data from a primary center were used for model development, with data from a second center serving as an independent external testing cohort. Systematic evaluation identified an optimal 10-biomarker LightGBM model that achieved outstanding discrimination on the external cohort, with an AUC of 0.926. Beyond its high accuracy, explainability analyses confirmed the model's predictions are driven by robust, clinically relevant markers of severe inflammation and metabolic dysfunction, reinforcing its trustworthiness. The final model was deployed as a publicly accessible web tool for real-time risk stratification. This work provides a powerful, externally validated, and explainable AI framework to augment clinical judgment, with strong potential to reduce diagnostic delays and improve outcomes for these devastating infections.
Insights
This study developed an explainable AI model to differentiate necrotizing fasciitis (NF) and osteomyelitis (OM) using blood tests. The model accurately distinguishes these severe infections, aiding clinical decisions.
Area of Science:
- Medical diagnostics
- Artificial intelligence in healthcare
- Infectious disease research
Background:
- Necrotizing fasciitis (NF) and osteomyelitis (OM) are severe infections with overlapping symptoms, complicating early diagnosis.
- Accurate differentiation is crucial for timely and appropriate treatment to prevent limb loss.
Purpose of the Study:
- To develop and validate an explainable machine learning model for distinguishing NF from OM.
- To improve diagnostic accuracy and speed for these limb-threatening infections.
Main Methods:
- A retrospective, multi-center cohort of 3415 patients (579 NF, 2836 OM) was analyzed.
- An explainable 10-biomarker LightGBM model was developed and validated using routine blood biomarkers.
- External validation was performed on data from a second independent center.
Main Results:
- The LightGBM model achieved an AUC of 0.926 on the external testing cohort.
- Explainability analyses confirmed predictions were based on clinically relevant markers of inflammation and metabolic dysfunction.
- The model was deployed as a publicly accessible web tool for risk stratification.
Conclusions:
- An externally validated, explainable AI framework can augment clinical judgment in diagnosing NF and OM.
- This AI tool has the potential to reduce diagnostic delays and improve patient outcomes for severe infections.
- The model provides a trustworthy and accurate method for risk stratification of patients with suspected NF or OM.
