Potential Use of a NEV Camera for Diagnostic Support of Carpal Tunnel Syndrome- Development of a Decision-Making Algorithm to Differentiate Carpal Tunnel Affected Hands from Control

Background: Carpal Tunnel Syndrome (CTS) is a prevalent neuropathy often requiring invasive diagnostic methods. This study explores the use of the New Energy Vision (NEV) camera, a non-invasive imaging tool, to detect CTS by analyzing visible light images of the hand. Objectives: To evaluate the diagnostic accuracy of the NEV camera in distinguishing CTS patients from controls and to identify image features associated with nerve damage. Methods: In a two-part study, Part 1 involved 103 participants (50 controls, 53 CTS patients) imaged with the NEV camera. Features extracted from these images were used to train a Support Vector Machine (SVM) classifier. Part 2 included 32 CTS patients with images from median nerve-damaged (MED) and ulnar nerve-normal (ULN) palm areas compared. Clinical validations included nerve conduction tests and questionnaires. Results: The SVM classifier achieved 93.33% accuracy with a confusion matrix of [[14, 1], [1, 14]] at a decision threshold of 0.7. Cross-validation showed a mean accuracy of 81.79%. In Part 2, significant differences (p < 0.05) were found in color proportions and Haralick texture features between MED and ULN areas. Conclusions: The NEV camera, combined with machine learning, demonstrates high accuracy in diagnosing CTS and reveals distinct image features linked to nerve damage, suggesting its potential as a non-invasive diagnostic tool.