Affiliation:
1. Universidad de Guanajuato
Abstract
In recent years, the use of image processing has increased considerably in the area of health sciences. The use of artificial intelligence techniques helps to strengthen diagnosis and/or to follow up medical treatments. In this work we present a method that allows the identification of Parkinson's disease by processing images corresponding to spirals and waves made by suspicious patients. This set of images was specially developed for this purpose and corresponds to a public database. Results obtained in two classification scenarios and four different learning methods are presented. Standard evaluation metrics are used to measure the performance of the implemented classification system. The results obtained are of the order of 90% accuracy which allows to see the effectiveness of the implemented methodology.
Reference12 articles.
1. [1] Micheli, F.E., Enfermedad de Parkinson y trastornos relacionados. 2006: Ed. Médica Panamericana.
2. [2] Rouhiainen, L.J.M.A.E., Inteligencia artificial. 2018.
3. [3] Juan, R.Q., C.M.J.R. Mario, and R.d.I.E. C, Electrónica y Computación, Redes neuronales artificiales para el procesamiento de imágenes, una revisión de la última década. 2011. 9(1): p. 7-16.
4. [4] Cancela, J., et al. A comprehensive motor symptom monitoring and management system: the bradykinesia case. in 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology. 2010. IEEE.
5. [5] Rigas, G., et al., Assessment of tremor activity in the Parkinson’s disease using a set of wearable sensors. 2012. 16(3): p. 478-487.