An IoT Approach to Personalised Remote Monitoring and Management of Epilepsy

Abstract

Living with the unpredictable nature of epilepsy is difficult. Not knowing when the next seizure will occur is grim enough, moreover when combined with further complexities associated with the disease epilepsy can become debilitating and often fatal.
Many current studies of epileptic seizure management disclose that an ultimate solution to drug-resistant epilepsy is still lacking. Also, although a variety of epilepsy devices exist the prevailing knowledge still resounds that epilepsy is not easily managed, this being due to its sheer complex nature.
An emerging approach is to personalise healthcare and this is known to be facilitated by the Internet of Things (IoT). Therefore, focusing upon personalised parameters that make epilepsy patients distinct from each other this thesis proposes that with IoT technologies there is a more accurate and refined way of remotely monitoring and managing the ‘individual’ patient. This is achieved by using classification techniques such as ontology development tools and clustering analysis to develop a Patient Profile Description Language (PPDL) and generate meaningful groups to categorize epilepsy patients. Ultimately a monitoring framework is developed to capture this personalised seizure data obtained from an IoT sensor-based device, which is positioned on different parts of the patient’s body.
This thesis discloses that it is ‘the individual profile’ that makes the difference in which IoT sensor-based device to choose and therefore the results used from this study are used to form a typical model or a PMP (Personalised Monitoring Plan) which recommends which IoT sensor-based device to use based on those very individual, personal characteristics of a given patient.
By integrating IoT sensor-based devices deployed remotely and personalised patient data into a combined monitoring framework the vision of personalisation is realised. Further revealed is some irrefutable evidence derived from patient profile analysis and experimental data that seizure detection using sensors positioned on different parts of a patents body ultimately makes an impact on the monitoring of epilepsy, endorsing that modern computer science is providing a timely chance for a more personalised approach to the monitoring and management of epilepsy.

Date of Award	9 Jun 2020
Original language	English
Awarding Institution	Edge Hill University
Supervisor	ELLA PEREIRA (Director of Studies), NEMITARI AJIENKA (Supervisor) & QUANBIN SUN (Supervisor)