Detection of Paroxysms in Long-Term, Single-Channel EEG-Monitoring of Patients with Typical Absence Seizures

Troels W Kjaer, Helge B D Sorensen, Sabine Groenborg, Charlotte R Pedersen, Jonas Duun-Henriksen, Troels W Kjaer, Helge B D Sorensen, Sabine Groenborg, Charlotte R Pedersen, Jonas Duun-Henriksen

Abstract

Absence seizures are associated with generalized 2.5-5 Hz spike-wave discharges in the electroencephalogram (EEG). Rarely are patients, parents, or physicians aware of the duration or incidence of seizures. Six patients were monitored with a portable EEG-device over four times 24 h to evaluate how easily outpatients are monitored and how well an automatic seizure detection algorithm can identify the absences. Based on patient-specific modeling, we achieved a sensitivity of 98.4% with only 0.23 false detections per hour. This yields a clinically satisfying performance with a positive predictive value of 87.1%. Portable EEG-recorders identifying paroxystic events in epilepsy outpatients are a promising tool for patients and physicians dealing with absence epilepsy. Albeit the small size of the EEG-device, some children still complained about the obtrusive nature of the device. We aim at developing less obtrusive though still very efficient devices, e.g., hidden in the ear canal or below the skin.

Keywords: Absence seizures; SVM; automatic seizure detection; epilepsy; single channel EEG.

Figures

FIGURE 1.
FIGURE 1.
Study protocol overview. Patients are monitored 24 hours on four independent days. At the first recording day, a standard scalp-EEG is performed at the hospital.
FIGURE 2.
FIGURE 2.
Experimental setup. Three electrodes were attached to the skin at approximate location of Fp1 (Ref), F7 and TP7. VD is the voltage divider that doubles the dynamic input range to Vpp.
FIGURE 3.
FIGURE 3.
Data and signal processing diagram. The processes within the dashed line are repeated in a 5-fold cross-validation scheme.
FIGURE 4.
FIGURE 4.
Relative number of paroxysms per 24-hours (normalized by maximum day) in relation to study day. The number of paroxysms decline during the study for all subject. For five out of six patients this is most likely explained by an increase in AED during the trial. By multiple recordings on the patients, the physician has a better chance of getting the AED dosage right.

References

    1. Heo K., Han S.-D., Lim S. R., Kim M. A., and Lee B. I., “Patient awareness of complex partial seizures,” Epilepsia, vol. 47, no. 11, pp. 1931–1935, Nov. 2006.
    1. Ebersole J. S. and Leroy R. F., “A direct comparison of ambulatory cassette and intensive inpatients EEG monitoring in detecting interictal abnormalities,” Electroencephalogr. Clin. Neurophysiol., vol. 53, no. P21, 1982.
    1. Looney D., et al. , “The in-the-ear recording concept: User-centered and wearable brain monitoring,” IEEE Pulse, vol. 3, no. 6, pp. 32–42, Nov. 2012.
    1. Ives J. R. and Woods J. F., “4-Channel 24 hour cassette recorder for longterm EEG monitoring of ambulatory patients,” Electroencephalogr. Clin. Neurophysiol., vol. 39, no. 1, pp. 88–92, Jul. 1975.
    1. Ives J. R. and Woods J. F., “A study of 100 patients with focal epilepsy using a 4-channel ambulatory cassette recorder,” in Proc. Third Int. Symp. Ambulatory Monitor., 1980, pp. 383–392.
    1. Faulkner H. J., Arima H., and Mohamed A., “The utility of prolonged outpatient ambulatory EEG,” Seizure, vol. 21, no. 7, pp. 491–495, Sep. 2012.
    1. de Feo M. R., Mecarelli O., Ricci G., and Rina M. F., “The utility of ambulatory EEG monitoring in typical absence seizures,” Brain Develop., vol. 13, no. 4, pp. 223–227, Jul. 1991.
    1. Sullivan J. E. and Dlugos D. J., “Idiopathic generalized epilepsy,” Current Treat. Opt. Neurol., vol. 6, no. 3, pp. 231–242, May 2004.
    1. Duun-Henriksen J., Madsen R. E., Remvig L. S., Thomsen C. E., Sorensen H. B. D., and Kjaer T. W., “Automatic detection of childhood absence epilepsy seizures: Toward a monitoring device,” Pediatric Neurol., vol. 46, no. 5, pp. 287–292, 2012.
    1. Rowan A. J., Meijer J. W. A., de Beer-Pawlikowski N., van der Geest P., and Meinardi H., “Valproate-ethosuximide combination therapy for refractory absence seizures,” Arch. Neurol., vol. 40, no. 13, pp. 797–802, Dec. 1983.
    1. Perucca E. and Meador K. J., “Adverse effects of antiepileptic drugs,” Acta Neurol. Scand., vol. 121, no. 181, pp. 30–35, 2005.
    1. Tenney J. R. and Glauser T. A., “The current state of absence epilepsy: Can we have your attention?” Epilepsy Currents, vol. 13, no. 3, pp. 40–135, May 2013.
    1. Sadleir L. G., Farrell K., Smith S., Connolly M. B., and Scheffer I. E., “Electroclinical features of absence seizures in childhood absence epilepsy,” Neurology, vol. 67, no. 3, pp. 413–418, Aug. 2006.
    1. Keilson M. J., Hauser W. A., Magrill J. P., and Tepperberg J., “Ambulatory cassette EEG in absence epilepsy,” Pediatric Neurol., vol. 3, no. 5, pp. 273–276, Oct. 1987.
    1. Mendizabal J. E. andNowack W. J., “Transitory cognitive impairment with brief generalized spike-wave paroxysm: A clinical counterexample to the three-second rule,” Clin. Electroencephalogr., vol. 27, no. 4, pp. 215–217, Oct. 1996.
    1. Holmes G. L., McKeever M., and Adamson M., “Absence seizures in children: Clinical and electroencephalographic features,” Ann. Neurol., vol. 21, no. 3, pp. 268–273, Mar. 1987.
    1. Westmijse I., Ossenblok P., Gunning B., and Van Luijtelaar G., “Onset and propagation of spike and slow wave discharges in human absence epilepsy: A MEG study,” Epilepsia, vol. 50, no. 12, pp. 2538–2548, Dec. 2009.
    1. Carrie J. R. and Frost J. D. Jr., “Clinical evaluation of a method for quantification of generalized spike-wave EEG patterns by computer during prolonged recordings,” Comput. Biomed. Res., vol. 10, no. 5, pp. 449–457, Oct. 1977.
    1. Ehrenberg B. L. and Penry J. K., “Computer recognition of generalized spike-wave discharges,” Electroencephalogr. Clin. Neurophysiol., vol. 41, no. 1, pp. 25–36, Jul. 1976.
    1. Koffler D. J. and Gotman J., “Automatic detection of spike-and-wave bursts in ambulatory EEG recordings,” Electroencephalogr. Clin. Neurophysiol., vol. 61, no. 2, pp. 165–180, Aug. 1985.
    1. Principe J. and Smith J. R., “Microcomputer-based system for the detection and quantification of petit mal epilepsy,” Comput. Biol. Med., vol. 12, no. 2, pp. 87–95, Dec. 1982.
    1. Xanthopoulos P., et al. , “A novel wavelet based algorithm for spike and wave detection in absence epilepsy,” in Proc. IEEE Int. Conf. Bioinf. Bioeng., May 2010, pp. 14–19.
    1. Duun-Henriksen J., Sørensen H. B. D., Kjær T. W., and Thomsen C. E., “Detection and prediction of epileptic seizures,” Ph.D. dissertation, Dept. Elect. Eng, Tech. Univ. Denmark, Kongens Lyngby, Denmark, 2012.
    1. Bloomfield P., Fourier Analysis of Time Series: An Introduction, 2nd ed. Hoboken, NJ, USA: Wiley, 2000.
    1. Yongli Z., Yungui Z., Weiming T., and Hongzhi C., “An improved feature selection algorithm based on MAHALANOBIS distance for network intrusion detection,” in Proc. Int. Conf. Sensor Netw. Secur. Technol. Privacy Commun. Syst., May 2013, pp. 69–73.
    1. Shoeb A., Edwards H., Connolly J., Bourgeois B., Treves S. T., and Guttag J., “Patient-specific seizure onset detection,” Epilepsy Behavior, vol. 5, no. 4, pp. 483–498, Aug. 2004.
    1. Henriksen J., et al. , “Automatic seizure detection: Going from sEEG to iEEG,” in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., Aug. 2010, pp. 2431–2434.
    1. Yen S.-J. and Lee Y.-S., “Cluster-based under-sampling approaches for imbalanced data distributions,” Expert Syst. Appl., vol. 36, no. 3, pp. 5718–5727, Apr. 2009.
    1. Chang C.-C. and Lin C.-J., “LIBSVM: A library for support vector machines,” ACM Trans. Intell. Syst. Technol., vol. 2, no. 3, pp. 27:1–27:27, 2011.
    1. Wang Y., Loparo K. A., Kelly M. R., and Kaplan R. F., “Evaluation of an automated single-channel sleep staging algorithm,” Nature Sci. Sleep, vol. 7, pp. 101–111, Jan. 2015.

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe