Utilizing machine learning to predict post-treatment outcomes in chronic non-specific neck pain patients undergoing
Ibrahim M Moustafa1,2,3, Dilber Uzun Ozsahin4,5,6, Mubarak Taiwo Mustapha5,6,7
1Department of Physiotherapy, College of Health Sciences, University of Sharjah, 27272, Sharjah, United Arab Emirates.
Scientific Reports
|May 23, 2024
Summary
Machine learning accurately predicts chronic neck pain outcomes. Models forecast changes in cervical lordotic angle, pain, and disability, aiding personalized rehabilitation strategies using cervical extension traction.
Area of Science:
- Rehabilitation Medicine
- Biomedical Engineering
- Data Science
Background:
- Chronic neck pain affects a significant patient population.
- Multimodal rehabilitation programs, including cervical extension traction (CET), are common treatments.
- Predicting treatment outcomes remains a challenge in optimizing patient care.
Purpose of the Study:
- To apply machine learning for predicting post-treatment outcomes in chronic neck pain patients.
- To identify pre-treatment variables that predict changes in cervical lordotic angle (CLA), pain, and disability.
- To integrate predictive modeling into conservative rehabilitation strategies.
Main Methods:
- Utilized pre-treatment demographic and clinical data from 570 chronic neck pain patients.
- Developed linear regression models using the sci-kit-learn library in Python.
- Input variables included age, BMI, CLA, head translation, disability index, pain score, and treatment parameters.
Main Results:
- Linear regression models demonstrated high precision and accuracy.
- Models explained 30-55% of the variability in post-treatment outcomes, with the highest for CLA.
- Identified key pre-treatment variables influencing treatment success.
Conclusions:
- Machine learning models can effectively predict outcomes for chronic neck pain.
- These models offer valuable insights for customizing interventions and optimizing rehabilitation.
- This study pioneers the integration of machine learning in spinal rehabilitation for improved patient care.
