Discrete Cosine Transform for the Analysis of Essential Tremor

Essential tremor (ET) in the most common movement disorder, being 20 times more common than Parkinson’s disease, and 50-70% of essential tremor cases are estimated to be genetic in origin. Archimedes spiral drawing is the gold standard tests to differentiate between both pathologies and also to detect ET. In this work, we explore the use of Discrete Cosine Transform related features from drawings as a part of a wide-ranging cross-study for the diagnosis of essential tremor. We compare the performance of these features against other classical and already analysed ones, with the aim of developing a very simple system using the smallest set of features but providing similar accuracy compared with other more complex systems. Then these new biomarkers will be integrated in future works with those obtained in the Biodonostia study. It should be highlighted that the use of this technology could provide undoubted benefits towards the development of more sustainable, low cost, high quality, non-invasive technologies. These systems are easily adaptable to the user and environment, and from a social and economic point of view can be very useful in real complex environments.