ABSTRACT
Epileptic seizure detection is traditionally done using video/electroencephalogram (EEG) monitoring, which is not applicable in a home situation. In recent years, attempts have been made to detect the seizures using other modalities. In this paper we investigate if a combined usage of accelerometers attached to the limbs and video data would increase the performance compared to a single modality approach. Therefore, we used two existing approaches for seizure detection in accelerometers and video and combined them using a linear discriminant analysis (LDA) classifier. The results for a combined detection have a better positive predictive value (PPV) of 95.00% compared to the single modality detection and reached a sensitivity of 83.33%.
- L. Chen, X. Yang, Y. Liu, D. Zeng, Y. Tang, B. Yan, X. Lin, L. Liu, H. Xu, and D. Zhou. Quantitative and trajectory analysis of movement trajectories in supplementary motor area seizures of frontal lobe epilepsy. Epilepsy & Behavior, 14(2):344--353, 2009.Google ScholarCross Ref
- I. Conradsen, S. Beniczky, P. Wolf, J. Henriksen, T. Sams, and H. B. D. Sorensen. Seizure onset detection based on a uni- or multi-modal intelligent seizure acquisition (UISA/MISA) system. 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2010), pages 3269--72, 2010.Google ScholarCross Ref
- K. Cuppens, C.-W. Chen, K. Wong, A. Van de Vel, L. Lagae, B. Ceulemans, T. Tuytelaars, S. Van Huffel, B. Vanrumste, and H. Aghajan. Using spatio-temporal interest points (STIP) for myoclonic jerk detection in nocturnal video. EMBC: 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, submitted, 2012.Google Scholar
- K. Cuppens, P. Karsmakers, A. Van de Vel, S. Luca, B. Bonroy, M. Milosevic, B. Ceulemans, L. Lagae, S. Van Huffel, and B. Vanrumste. Accelerometer based home monitoring for detection of nocturnal hypermotor seizures with estimation of probability density function. Internal report, 2012.Google Scholar
- B. Greene, G. Boylan, R. Reilly, P. de Chazal, and C. S. Combination of EEG and ECG for improved automatic neonatal seizure detection. Clin Neurophysiol, 118(6):1348--59, 2007.Google ScholarCross Ref
- N. B. Karayiannis, G. Z. Tao, J. D. Frost, M. S. Wise, R. A. Hrachovy, and E. M. Mizrahi. Automated detection of videotaped neonatal seizures based on motion segmentation methods. Clinical Neurophysiology, 117(7):1585--1594, 2006.Google ScholarCross Ref
- I. Laptev. On space-time interest points. International Journal of Computer Vision, 64(2-3):107--123, 2005. Google ScholarDigital Library
- J. Lockman, R. S. Fisher, and D. M. Olson. Detection of seizure-like movements using a wrist accelerometer. Epilepsy & Behavior, 20(4):638--641, 2011.Google ScholarCross Ref
- G. J. McLachlan. Discriminant analysis and statistical pattern recognition. Wiley Series in Probability and Mathematical Statistics, 1992.Google Scholar
- T. M. E. Nijsen, R. M. Aarts, P. J. M. Cluitmans, and P. A. M. Griep. Time-frequency analysis of accelerometry data for detection of myoclonic seizures. IEEE Transactions on Information Technology in Biomedicine, 14(5):1197--1203, 2010. Google ScholarDigital Library
- D. Ruta and B. Gabrys. An overview of classifier fusion methods. Computing and Information Systems, (7):1--10, 2000.Google Scholar
- P. Varshney. Multisensor data fusion. Electronics and Communications Engineering Journal, 9:245--253, 1997.Google ScholarCross Ref
- D. Wolpert. Stacked generalization. Neural Networks, pages 241--259, 1992. Google ScholarDigital Library
- T.-F. Wu, C.-J. Lin, and R. C. Weng. Probability estimates for multi-class classification by pairwise coupling. Journal of Machine Learning Research, 5:975--1005, 2004. Google ScholarDigital Library
Index Terms
- Integrating video and accelerometer signals for nocturnal epileptic seizure detection
Recommendations
Machine learning-based EEG signals classification model for epileptic seizure detection
AbstractThe detection of epileptic seizures by classifying electroencephalography (EEG) signals into ictal and interictal classes is a demanding challenge, because it identifies the seizure and seizure-free states of an epileptic patient. In previous ...
Epileptic Seizure Detection using Bipolar Singular Value Decomposition
BIOSTEC 2015: Proceedings of the International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 4We propose a robust method for automated detection of epileptic seizures using intracranial electroencephalogram (iEEG) recordings with two electrodes. The state-of-the-art seizure detection methods suffer from high number of false detections, even when ...
Epileptic seizure detection using dynamical preprocessing (STLmax)
Quantitative neuroscienceThe long-term properties of the Short-term largest Lyapunov exponents (STLmax) of EEG have been used successfully in epilepsy seizure prediction. STLmax profiles also show short-term patterns characterizing seizures that can be used for detection ...
Comments