Research Article
A Novel Approach for Seizure Classification Using Patient Specific Triggers: Pilot Study
@INPROCEEDINGS{10.1007/978-3-030-67540-0_29, author={Jamie Pordoy and Ying Zhang and Nasser Matoorian}, title={A Novel Approach for Seizure Classification Using Patient Specific Triggers: Pilot Study}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 16th EAI International Conference, CollaborateCom 2020, Shanghai, China, October 16--18, 2020, Proceedings, Part II}, proceedings_a={COLLABORATECOM PART 2}, year={2021}, month={1}, keywords={Multi-modal Machine learning Epilepsy Seizure Patient-specific}, doi={10.1007/978-3-030-67540-0_29} }- Jamie Pordoy
Ying Zhang
Nasser Matoorian
Year: 2021
A Novel Approach for Seizure Classification Using Patient Specific Triggers: Pilot Study
COLLABORATECOM PART 2
Springer
DOI: 10.1007/978-3-030-67540-0_29
Abstract
With advancements in personalised medicine, healthcare delivery systems have moved away from the one-size-fits-all approach towards tailored treatments that meet the needs of individuals and specific subgroups. As nearly one-third of those diagnosed with epilepsy are classed as refractory and are resistant to antiepileptic medication, there is a need for a personalised method of detecting epileptic seizures. Epidemiological studies show that up to 91% of those diagnosed identify one or more triggers as the causation of their seizure onset. These triggers are patient-specific and can affect those diagnosed in different ways dependent on each person’s idiosyncratic tolerance and threshold levels. Whilst these triggers are known to induce seizure onset, only a few studies have even considered their use as a preventive component. Therefore, this pilot study investigates the use of patient-specific triggers (PST) in diagnosed epileptics, and whether they can be used as an additional modality when detecting seizures. This study used a precision medicine approach with artificial intelligence (AI), to train and test several patient-specific algorithms that classified epileptic seizures based on the PST of each participant. Experimental results show accuracy, sensitivity, and specificity scores of 94.73%, 96.90% and 93.33% for participant 1 and 96.87%, 96.96% and 96.77% for participant 2, respectively.
