Identification of Relevant ECG Features for Epileptic Seizure Prediction Using Interpretable Machine Learning
Abtahi, Azra LU ; Ryvlin, Philippe and Aminifar, Amir LU
(2025)
In IEEE Access
13.
p.111293-111303
- Abstract
Epileptic seizure prediction holds the potential to enhance the quality of life for individuals with epilepsy by enabling the possibility of timely administration of medication and first aid, as well as preventing subsequent accidents. In this paper, we consider the well-established Heart Rate Variability (HRV) and Lorenz features, and augment them with the electrocardiogram (ECG) multifractality features for the first time for seizure prediction. Our experimental results demonstrate that incorporating multifractality features significantly enhances epileptic seizure prediction, with a 7.5% improvement over using only HRV features and a 6.9% improvement over using both HRV and Lorenz features. We also investigate the significance and... (More)
Epileptic seizure prediction holds the potential to enhance the quality of life for individuals with epilepsy by enabling the possibility of timely administration of medication and first aid, as well as preventing subsequent accidents. In this paper, we consider the well-established Heart Rate Variability (HRV) and Lorenz features, and augment them with the electrocardiogram (ECG) multifractality features for the first time for seizure prediction. Our experimental results demonstrate that incorporating multifractality features significantly enhances epileptic seizure prediction, with a 7.5% improvement over using only HRV features and a 6.9% improvement over using both HRV and Lorenz features. We also investigate the significance and impact of features in a seizure prediction Machine Learning (ML) model utilizing ECG signals, aiming to shed light on the intricate relationship between cardiac function and epileptic seizures. We employ SHAP (SHapley Additive exPlanations), an interpretability framework, to interpret the prediction patterns. Based on our analysis, multifractality features are among the most important features in seizure prediction, capturing patterns that are not captured by the HRV and Lorenz features.
(Less)
- author
- Abtahi, Azra
LU
; Ryvlin, Philippe
and Aminifar, Amir
LU
- organization
-
- LTH Profile Area: Engineering Health
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- Networks and Security (research group)
- Department of Electrical and Information Technology
- LTH Profile Area: Water
- LU Profile Area: Natural and Artificial Cognition
- LTH Profile Area: AI and Digitalization
- publishing date
- 2025
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Electrocardiogram (ECG), epilepsy, explainable machine learning, interpretability, multifractality, seizure prediction, SHAP value
- in
- IEEE Access
- volume
- 13
- pages
- 11 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:105009466727
- ISSN
- 2169-3536
- DOI
- 10.1109/ACCESS.2025.3583461
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2013 IEEE.
- id
- fe769e38-e707-4b3a-8000-77addd15a13e
- date added to LUP
- 2026-01-19 14:11:02
- date last changed
- 2026-01-19 14:12:15
@article{fe769e38-e707-4b3a-8000-77addd15a13e,
abstract = {{<p>Epileptic seizure prediction holds the potential to enhance the quality of life for individuals with epilepsy by enabling the possibility of timely administration of medication and first aid, as well as preventing subsequent accidents. In this paper, we consider the well-established Heart Rate Variability (HRV) and Lorenz features, and augment them with the electrocardiogram (ECG) multifractality features for the first time for seizure prediction. Our experimental results demonstrate that incorporating multifractality features significantly enhances epileptic seizure prediction, with a 7.5% improvement over using only HRV features and a 6.9% improvement over using both HRV and Lorenz features. We also investigate the significance and impact of features in a seizure prediction Machine Learning (ML) model utilizing ECG signals, aiming to shed light on the intricate relationship between cardiac function and epileptic seizures. We employ SHAP (SHapley Additive exPlanations), an interpretability framework, to interpret the prediction patterns. Based on our analysis, multifractality features are among the most important features in seizure prediction, capturing patterns that are not captured by the HRV and Lorenz features.</p>}},
author = {{Abtahi, Azra and Ryvlin, Philippe and Aminifar, Amir}},
issn = {{2169-3536}},
keywords = {{Electrocardiogram (ECG); epilepsy; explainable machine learning; interpretability; multifractality; seizure prediction; SHAP value}},
language = {{eng}},
pages = {{111293--111303}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Access}},
title = {{Identification of Relevant ECG Features for Epileptic Seizure Prediction Using Interpretable Machine Learning}},
url = {{http://dx.doi.org/10.1109/ACCESS.2025.3583461}},
doi = {{10.1109/ACCESS.2025.3583461}},
volume = {{13}},
year = {{2025}},
}