Seizure prediction with long-term iEEG recordings: What can we learn from data nonstationarity?
- Resource Type
- Conference
- Authors
- Yang, Hongliu; Eberlein, Matthias; Muller, Jens; Tetzlaff, Ronald
- Source
- 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) Bioinformatics and Biomedicine (BIBM), 2021 IEEE International Conference on. :1-6 Dec, 2021
- Subject
- Bioengineering
Computing and Processing
Signal Processing and Analysis
Training
Schedules
Machine learning algorithms
Image color analysis
Heuristic algorithms
Time series analysis
Training data
- Language
Repeated epileptic seizures impair around 65 million people worldwide and a successful prediction of seizures could significantly h elp p atients suffering from refractory epilepsy. For two dogs with yearlong intracranial electroencephalography (iEEG) recordings, we studied the influence of time series nonstationarity on the performance of seizure prediction using in-house developed machine learning algorithms. We observed a long-term evolution on the scale of weeks or months in iEEG time series that may be represented as switching between certain meta-states. To better predict impending seizures, retraining of prediction algorithms is therefore necessary and the retraining schedule should be adjusted to the change in meta-states. There is evidence that the nature of seizure-free interictal clips also changes with the transition between meta-states, which has been shown relevant for seizure prediction.