ECG‐based epileptic seizure prediction: Challenges of current data‐driven models
Abstract Objective Up to a third of patients with epilepsy fail to achieve satisfactory seizure control. A reliable method of predicting seizures would alleviate psychological and physical impact. Dysregulation in heart rate variability (HRV) has been found to precede epileptic seizures and may serv...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-02-01
|
| Series: | Epilepsia Open |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/epi4.13073 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206509619904512 |
|---|---|
| author | Sotirios Kalousios Jens Müller Hongliu Yang Matthias Eberlein Ortrud Uckermann Gabriele Schackert Witold H. Polanski Georg Leonhardt |
| author_facet | Sotirios Kalousios Jens Müller Hongliu Yang Matthias Eberlein Ortrud Uckermann Gabriele Schackert Witold H. Polanski Georg Leonhardt |
| author_sort | Sotirios Kalousios |
| collection | DOAJ |
| description | Abstract Objective Up to a third of patients with epilepsy fail to achieve satisfactory seizure control. A reliable method of predicting seizures would alleviate psychological and physical impact. Dysregulation in heart rate variability (HRV) has been found to precede epileptic seizures and may serve as an extracerebral predictive biomarker. This study aims to identify the preictal HRV dynamics and unveil the factors impeding the clinical application of ECG‐based seizure prediction. Methods Thirty‐nine adult patients (eight women; median age: 38, [IQR = 31, 56.5]) with 252 seizures were included. Each patient had more than three recorded epileptic seizures, each at least 2 hours apart. For each seizure, one hour of ECG prior to seizure onset was analyzed and 97 HRV features were extracted from overlapping three‐minute windows with 10s stride. Two separate patient‐specific experiments were performed using a support vector machine (SVM). Firstly, the separability of training data was examined in a non‐causal trial. Secondly, the prediction was attempted in pseudo‐prospective conditions. Finally, visualized HRV data, clinical metadata, and results were correlated. Results The mean receiver operating characteristic (ROC) area under the curve (AUC) for the non‐causal experiment was 0.823 (±0.12), with 208 (82.5%) seizures achieving an improvement over chance (IoC) classification score (p < 0.05, Hanley & McNeil test). In pseudo‐prospective classification, the ROC‐AUC was 0.569 (±0.17), and 86 (49.4%) seizures were classified with IoC. Off‐sample optimized SVMs failed to improve performance. Major limiting factors identified include non‐stationarity, variable preictal duration and dynamics. The latter is expressed as both inter‐seizure onset zone (SOZ) and intra‐SOZ variability. Significance The pseudo‐prospective preictal classification achieving IoC in approximately half of tested seizures suggests the presence of genuine preictal HRV dynamics, but the overall performance does not warrant clinical application at present. The limiting factors identified are often overlooked in non‐causal study designs. While current deterministic prediction methods prove inadequate, probabilistic approaches may offer a promising alternative. Plain Language Summary Many patients with epilepsy suffer from uncontrollable seizures and would greatly benefit from a reliable seizure prediction method. Currently, no such system is available to meet this need. Previous studies suggest that changes in the electrocardiogram (ECG) precede seizures by several minutes. In our work, we evaluated whether variations in heart rate could be used to predict epileptic seizures. Our findings indicate that we are still far from achieving results suitable for clinical application and highlight several limiting factors of present seizure prediction approaches. |
| format | Article |
| id | doaj-art-baa11bff3d794613be58db1fd1e75ab8 |
| institution | Kabale University |
| issn | 2470-9239 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Epilepsia Open |
| spelling | doaj-art-baa11bff3d794613be58db1fd1e75ab82025-02-07T09:12:45ZengWileyEpilepsia Open2470-92392025-02-0110114315410.1002/epi4.13073ECG‐based epileptic seizure prediction: Challenges of current data‐driven modelsSotirios Kalousios0Jens Müller1Hongliu Yang2Matthias Eberlein3Ortrud Uckermann4Gabriele Schackert5Witold H. Polanski6Georg Leonhardt7Department of Neurosurgery, Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universität Dresden Dresden GermanyTU Dresden, Faculty of Electrical and Computer Engineering Institute of Circuits and Systems Dresden GermanyTU Dresden, Faculty of Electrical and Computer Engineering Institute of Circuits and Systems Dresden GermanyTU Dresden, Faculty of Electrical and Computer Engineering Institute of Circuits and Systems Dresden GermanyDepartment of Neurosurgery, Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universität Dresden Dresden GermanyDepartment of Neurosurgery, Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universität Dresden Dresden GermanyDepartment of Neurosurgery, Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universität Dresden Dresden GermanyDepartment of Neurosurgery, Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universität Dresden Dresden GermanyAbstract Objective Up to a third of patients with epilepsy fail to achieve satisfactory seizure control. A reliable method of predicting seizures would alleviate psychological and physical impact. Dysregulation in heart rate variability (HRV) has been found to precede epileptic seizures and may serve as an extracerebral predictive biomarker. This study aims to identify the preictal HRV dynamics and unveil the factors impeding the clinical application of ECG‐based seizure prediction. Methods Thirty‐nine adult patients (eight women; median age: 38, [IQR = 31, 56.5]) with 252 seizures were included. Each patient had more than three recorded epileptic seizures, each at least 2 hours apart. For each seizure, one hour of ECG prior to seizure onset was analyzed and 97 HRV features were extracted from overlapping three‐minute windows with 10s stride. Two separate patient‐specific experiments were performed using a support vector machine (SVM). Firstly, the separability of training data was examined in a non‐causal trial. Secondly, the prediction was attempted in pseudo‐prospective conditions. Finally, visualized HRV data, clinical metadata, and results were correlated. Results The mean receiver operating characteristic (ROC) area under the curve (AUC) for the non‐causal experiment was 0.823 (±0.12), with 208 (82.5%) seizures achieving an improvement over chance (IoC) classification score (p < 0.05, Hanley & McNeil test). In pseudo‐prospective classification, the ROC‐AUC was 0.569 (±0.17), and 86 (49.4%) seizures were classified with IoC. Off‐sample optimized SVMs failed to improve performance. Major limiting factors identified include non‐stationarity, variable preictal duration and dynamics. The latter is expressed as both inter‐seizure onset zone (SOZ) and intra‐SOZ variability. Significance The pseudo‐prospective preictal classification achieving IoC in approximately half of tested seizures suggests the presence of genuine preictal HRV dynamics, but the overall performance does not warrant clinical application at present. The limiting factors identified are often overlooked in non‐causal study designs. While current deterministic prediction methods prove inadequate, probabilistic approaches may offer a promising alternative. Plain Language Summary Many patients with epilepsy suffer from uncontrollable seizures and would greatly benefit from a reliable seizure prediction method. Currently, no such system is available to meet this need. Previous studies suggest that changes in the electrocardiogram (ECG) precede seizures by several minutes. In our work, we evaluated whether variations in heart rate could be used to predict epileptic seizures. Our findings indicate that we are still far from achieving results suitable for clinical application and highlight several limiting factors of present seizure prediction approaches.https://doi.org/10.1002/epi4.13073ECGHRVpreictalseizure predictionwarning system |
| spellingShingle | Sotirios Kalousios Jens Müller Hongliu Yang Matthias Eberlein Ortrud Uckermann Gabriele Schackert Witold H. Polanski Georg Leonhardt ECG‐based epileptic seizure prediction: Challenges of current data‐driven models Epilepsia Open ECG HRV preictal seizure prediction warning system |
| title | ECG‐based epileptic seizure prediction: Challenges of current data‐driven models |
| title_full | ECG‐based epileptic seizure prediction: Challenges of current data‐driven models |
| title_fullStr | ECG‐based epileptic seizure prediction: Challenges of current data‐driven models |
| title_full_unstemmed | ECG‐based epileptic seizure prediction: Challenges of current data‐driven models |
| title_short | ECG‐based epileptic seizure prediction: Challenges of current data‐driven models |
| title_sort | ecg based epileptic seizure prediction challenges of current data driven models |
| topic | ECG HRV preictal seizure prediction warning system |
| url | https://doi.org/10.1002/epi4.13073 |
| work_keys_str_mv | AT sotirioskalousios ecgbasedepilepticseizurepredictionchallengesofcurrentdatadrivenmodels AT jensmuller ecgbasedepilepticseizurepredictionchallengesofcurrentdatadrivenmodels AT hongliuyang ecgbasedepilepticseizurepredictionchallengesofcurrentdatadrivenmodels AT matthiaseberlein ecgbasedepilepticseizurepredictionchallengesofcurrentdatadrivenmodels AT ortruduckermann ecgbasedepilepticseizurepredictionchallengesofcurrentdatadrivenmodels AT gabrieleschackert ecgbasedepilepticseizurepredictionchallengesofcurrentdatadrivenmodels AT witoldhpolanski ecgbasedepilepticseizurepredictionchallengesofcurrentdatadrivenmodels AT georgleonhardt ecgbasedepilepticseizurepredictionchallengesofcurrentdatadrivenmodels |