Coherent False Seizure Prediction in Epilepsy, Coincidence or Providence?
| Autor: | Matthias Eberlein, Levin Kuhlmann, Georg Leonhardt, Jens Müller, Ortrud Uckermann, Ronald Tetzlaff, Hongliu Yang |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Adult
Male Signal Processing (eess.SP) FOS: Computer and information sciences Information transfer Computer Science - Machine Learning Databases Factual Computer science Coincidence Machine Learning (cs.LG) Correlation Epilepsy Seizures Physiology (medical) medicine FOS: Electrical engineering electronic engineering information engineering Humans Electrical Engineering and Systems Science - Signal Processing Aged business.industry Deep learning Electroencephalography Pattern recognition Middle Aged medicine.disease Sensory Systems Outcome (probability) Prediction algorithms Neurology Classification methods Female Neural Networks Computer Neurology (clinical) Artificial intelligence business Forecasting |
| DOI: | 10.48550/arxiv.2110.13550 |
| Popis: | Seizure forecasting using machine learning is possible, but the performance is far from ideal, as indicated by many false predictions and low specificity. Here, we examine false and missing alarms of two algorithms on long-term datasets to show that the limitations are less related to classifiers or features, but rather to intrinsic changes in the data. We evaluated two algorithms on three datasets by computing the correlation of false predictions and estimating the information transfer between both classification methods. For 9 out of 12 individuals both methods showed a performance better than chance. For all individuals we observed a positive correlation in predictions. For individuals with strong correlation in false predictions we were able to boost the performance of one method by excluding test samples based on the results of the second method. Substantially different algorithms exhibit a highly consistent performance and a strong coherency in false and missing alarms. Hence, changing the underlying hypothesis of a preictal state of fixed time length prior to each seizure to a proictal state is more helpful than further optimizing classifiers. The outcome is significant for the evaluation of seizure prediction algorithms on continuous data. Comment: 23 pages, 7 figures, accepted for publication in Clinical Neurophysiology |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|