Reflex sensors for telemedicine applications

[摘要] A solution is sought for the measurement of human deep tendon reflexes as part ofa comprehensive patient condition monitoring system for use in a telemedicinecontext. This study focused on the development, testing and performanceevaluation of a prototype compact patellar tendon reflex measurement system thatis able to provide a quantitative reflex evaluation for use by medical practitionersand in a telemedicine environment. A prototype system was developed that makesuse of Xsens MTx orientation sensors, force-sensing resistors and anelectromyogram (EMG) to measure the reflex response. Suitable parametersidentified for analysis included the change in pitch, angular velocity andacceleration of the lower leg, the EMG response, the tendon impact, and variouslatencies associated with these measurements. Other information consideredincluded the age, mass, and physical dimensions of the test subject. Clinicaltesting was performed to collect data to evaluate the system performance.Subjective reflex evaluations were conducted by three doctors according to astandard reflex grading scale using video recordings of the tests. Self-organizingmaps and multi-layer feed-forward (MLFF) artificial neural networks (ANNs)were used to analyze the collected data with the aim of pattern identification, dataclassification and reflex grading prediction. It was found that the MLFF networkdelivered the correct reflex grading with an accuracy of 85%, which was of thesame order as the rate of differences between the subjective reflex evaluationsperformed by the doctors (80%). Furthermore, analysis of the data suggested thatcertain parameters were not necessary for the autonomous evaluation, such asEMG data and the tendon impact. The use of ANNs to analyze a reflexmeasurement as proposed by this study offers an accurate, repeatable and conciserepresentation of the reflex that is familiar to doctors and suitable for use in ageneral clinical setting or for telemedicine purposes.

[发布机构] Stellenbosch University