Related Experiment Video
Updated: Jun 29, 2025
06:31
Author Spotlight: Insight Into Innovations in Spinal Cord Injury Research
Published on: January 19, 2024
1.9K
Prediction model for spinal cord injury in spinal tuberculosis patients using multiple machine learning algorithms: a
Sitan Feng1, Shujiang Wang2, Chong Liu1
1Department of Spine and Osteopathy Ward, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, People's Republic of China.
Scientific Reports
|April 2, 2024
Summary
This study identifies key factors for predicting spinal cord injury (SCI) in spinal tuberculosis (STB) patients. A machine learning model using random forest effectively predicts SCI risk, aiding early intervention.
Area of Science:
- Spinal cord injury research
- Machine learning in medicine
- Tuberculosis complications
Background:
- Spinal cord injury (SCI) is a severe complication of spinal tuberculosis (STB), potentially causing paralysis.
- Early identification of SCI risk in STB patients is crucial for timely intervention.
Purpose of the Study:
- To identify clinical factors associated with SCI in STB patients.
- To develop and validate a predictive model for SCI in STB patients.
Main Methods:
- Utilized machine learning algorithms, including random forest (RF), to build predictive models.
- Evaluated model performance using ROC curves, AUC, calibration, DCA, and PR curves.
- Validated the optimal model on an external prospective cohort and deployed it via a web app.
Main Results:
- The RF model achieved an AUC of 0.816 on the test set.
- MONO (monocyte count) was identified as the primary predictor of SCI in STB patients.
- The model incorporated ten clinical characteristics for prediction.
Conclusions:
- The developed RF predictive model offers an efficient and rapid method for forecasting SCI risk in STB patients.
- This tool can assist clinicians in identifying high-risk individuals for proactive management.
