Related Experiment Video
Updated: Jun 11, 2025
Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury
Published on: June 21, 2019
A sustainable artificial-intelligence-augmented digital care pathway for epilepsy: Automating seizure tracking based
Pantea Keikhosrokiani1,2, Minna Isomursu1,2, Johanna Uusimaa3,4
1Empirical Software Engineering in Software, Systems, and Services, University of Oulu, Oulu, Finland.
Objective:
Scalp electroencephalograms (EEGs) are critical for neurological evaluations, particularly in epilepsy, yet they demand specialized expertise that is often lacking in many regions. Artificial intelligence (AI) offers potential solutions to this gap. While existing AI models address certain aspects of EEG analysis, a fully automated system for routine EEG interpretation is required for effective epilepsy management and healthcare professionals' decision-making. This study aims to develop an AI-augmented model for automating EEG seizure tracking, thereby supporting a sustainable digital care pathway for epilepsy (DCPE). The goal is to improve patient monitoring, facilitate collaborative decision-making, ensure timely medication adherence, and promote patient compliance.
Method:
The study proposes an AI-augmented framework using machine learning, focusing on quantitative analysis of EEG data to automate DCPE. A focus group discussion was conducted with healthcare professionals to find the problem of the current digital care pathway and assess the feasibility, usability, and sustainability of the AI-augmented system in the digital care pathway.
Results:
The study found that a combination of random forest with principal component analysis and support vector machines with KBest feature selection achieved high accuracy rates of 96.52% and 95.28%, respectively. Additionally, the convolutional neural networks model outperformed other deep learning algorithms with an accuracy of 97.65%. The focus group discussion revealed that automating the diagnostic process in digital care pathway could reduce the time needed to diagnose epilepsy. However, the sustainability of the AI-integrated framework depends on factors such as technological infrastructure, skilled personnel, training programs, patient digital literacy, financial resources, and regulatory compliance.
Conclusion:
The proposed AI-augmented system could enhance epilepsy management by optimizing seizure tracking accuracy, improving monitoring and timely interventions, facilitating collaborative decision-making, and promoting patient-centered care, thereby making the digital care pathway more sustainable.
