Related Experiment Video
Updated: May 1, 2026
04:08
Metacarpal Small Incision for Carpal Tunnel Syndrome
Published on: April 5, 2024
2.3K
Machine learning-based prediction model for paresthesia improvement after open carpal tunnel release: a preliminary
Takahiro Yamazaki1, Yusuke Matsuura2, Takuto Takeda2
1Department of Orthopaedic Surgery, Graduate school of Medicine, Chiba University, 1-8-1 Inohana Chuo-ku, Chiba, Chiba, 260-8670, Japan. taka-0407@hotmail.co.jp.
BMC Musculoskeletal Disorders
|April 30, 2026
Summary
A new machine learning model accurately predicts paresthesia improvement after carpal tunnel surgery. Key factors include distal motor latency, age, and disease duration, aiding preoperative planning.
Area of Science:
- Orthopedics
- Neurosurgery
- Medical Informatics
Background:
- Carpal tunnel syndrome (CTS) is a common hand neuropathy.
- Surgery offers good outcomes, but persistent paresthesia occurs postoperatively.
- Predicting postoperative paresthesia improvement is crucial for patient management.
Purpose of the Study:
- Develop and evaluate a machine learning model to predict paresthesia improvement after carpal tunnel release surgery.
- Identify key clinical factors influencing surgical outcomes.
- Enhance preoperative counseling and treatment strategies.
Main Methods:
- Retrospective analysis of 94 hands from 83 patients undergoing carpal tunnel release.
- Paresthesia improvement assessed at 1-year follow-up on a 10-point scale (0-1 excellent).
- Compared Support Vector Machine (SVM), Random Forest, and Logistic Regression models using AUC, accuracy, precision, and recall.
Main Results:
- 56.4% of patients achieved excellent paresthesia improvement.
- Optimized SVM model showed strong performance: AUC 0.852, accuracy 78.9%, precision 88.9%, recall 72.7%.
- Top predictors: distal motor latency (DML), age, disease duration, thenar atrophy, thumb opposition deficit.
Conclusions:
- A preliminary machine learning model accurately predicts excellent paresthesia improvement post-CTS surgery.
- The model utilizes five easily accessible clinical parameters.
- This pilot study supports developing advanced prediction tools for surgical planning.
