Carpal tunnel syndrome (CTS) is a common condition characterized by hand dysfunction
due to median nerve compression.
Orthopedic surgeons often detect signs of the symptoms to screen for CTS;
however, it is difficult to distinguish other diseases with symptoms similar to those of CTS.
We previously introduced a method of evaluating fine hand movements
to screen for cervical myelopathy (CM).
The present work applies this method to screen for CTS,
using videos of specific hand gestures to measure their quickness.
Machine learning models are used to evaluate the gestures
to estimate the probability that a patient has CTS.
We cross-validated the models to evaluate our method’s effectiveness in screening for CTS.
The results showed that the sensitivity and specificity
were 90.0% and 85.3%, respectively.
Furthermore, we found that our method can also be used to distinguish CTS and CM
and may enable earlier detection and treatment of similar neurological diseases.