Automatic diagnosis of carpal tunnel syndrome by applying existing and novel signal characteristics (Master thesis)
Carpal Tunnel Syndrome (CTS) is a medical situation where the median nerve is compressed while traveling through the tunel of human wrist. The resulting symptoms affect the 5% of the general population and the diagnosis of the syndrome is mainly based on Nerve Conduction Studies (NCS), a procedure of electrical conduction of finger nerves. The resulting signals are inspected by the neuro-physiologists and specific characteristics are measured in order to decide about the existence of the syndrome. The diagnosis of CTS is still controversial. Many researchers claim that since no more accurate method has been found, the NCS (Nerve Conduction Studies) should be considered as the gold standard of CTS diagnosis, while others insist that the remarkable instances of false negative results and the absence of correlation between NCS findings and clinical symptoms should lead to the establishment of an alternative method of CTS grading scale. In this thesis, after evaluating the existing signal features, we propose two additional techniques to the diagnosis of CTS; the first one consists of more geometric characteristics of the signal than those that are applied today and the second one is a feature which arises from the implementation of an algorithm called Dynamic Time Warping and examine if it can identify patterns in our time-series data. Our results show that geometric characteristics in addition to Dynamic Time Warping feature can ameliorate the accuracy of our model to predict the CTS grading severity and also increase the sensitivity and specificity values of today methods.
|Institution and School/Department of submitter:||Πανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Η/Υ & Πληροφορικής|
|Subject classification:||Carpal tunnel syndrome|
|Keywords:||Σύνδρομο του καρπιαίου σωλήνα,Δυναμική στρέβλωσης του χρόνου,CTS,DTW,Dynamic time warping|
|Appears in Collections:||Διατριβές Μεταπτυχιακής Έρευνας (Masters)|
Files in This Item:
|Μ.Ε. ΚΟΝΤΟΓΙΑΝΝΗΣ ΠΡΟΚΟΠΙΟΣ 2017.pdf||1.72 MB||Adobe PDF||View/Open|
Please use this identifier to cite or link to this item:This item is a favorite for 0 people.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.