Desarrollo de un prototipo de dispositivo basado en prendas tecnológicas para la asistencia inmediata en personas con epilepsia

Abstract

Epilepsy is characterized by the recurrence of epileptic seizures that affect secondary physiological changes in the patient. This leads to a series of adverse events at the time of a seizure in an uncontrolled environment and without medical help, which further increases the risk of the patient, especially in people with refractory epilepsy where modern pharmacology is not able to control the seizures Traditional detection methods based on clinical wired monitoring systems are not adequate for crisis detection and long-term outdoor monitoring. For these reasons, this project proposes a system that allows the detection of generalized tonic-clonic seizures in patients to alert family members or medical personnel for immediate assistance, based on a portable device (bracelet), a mobile application and a Classifier Support Vector Machine deployed in a system based on cloud computing. In the proposed approach we use Accelerometry (ACC), Electromyography (ECG) and Electrodermal Activity (EDA) as measurement signals for the development of the bracelet, an automatic learning algorithm (SVM) is used to discriminate between a seizure and non-convulsion. In addition, the high level architecture of the system is described, as well as the implementation of the ecosystem based on Cloud Computing for the execution of the algorithm and the communication of the mobile application with bracelet.

For the development of the system a methodology based on the treatise of Karl T. Ulrich "Design and development of products and methodology of Jesus David Cardona Quiroz" Development of multimedia systems "was proposed. The development of the system can be said to include two major components, the first research component where a state of the art about the symptoms and effects of a tonic-clonic seizure is performed in order to analyze the patients' problems. Also, the necessary technology to develop the system, detection methods and algorithms, and software architectures in the cloud to be taken into account for the design and production of the system. The second component includes everything related to the production of the system where the device used by the user is designed and developed, as well as the development of the algorithm to detect the seizure and the servers needed to host the algorithm and display the alert

Finally, the system is put to the test in a sample of volunteers using the prototype during the development of their daily activities, in order to evaluate their performance and integral functioning