Statistical Model-Based Classification to Detect Patient-Specific Spike-and-Wave in EEG Signals
Spike-and-wave discharge (SWD) pattern detection in electroencephalography (EEG) is a crucial signal processing problem in epilepsy applications. It is particularly important for overcoming time-consuming, difficult, and error-prone manual analysis of long-term EEG recordings. This paper presents a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/9/4/85 |
| _version_ | 1797549458707185664 |
|---|---|
| author | Antonio Quintero-Rincón Valeria Muro Carlos D’Giano Jorge Prendes Hadj Batatia |
| author_facet | Antonio Quintero-Rincón Valeria Muro Carlos D’Giano Jorge Prendes Hadj Batatia |
| author_sort | Antonio Quintero-Rincón |
| collection | DOAJ |
| description | Spike-and-wave discharge (SWD) pattern detection in electroencephalography (EEG) is a crucial signal processing problem in epilepsy applications. It is particularly important for overcoming time-consuming, difficult, and error-prone manual analysis of long-term EEG recordings. This paper presents a new method to detect SWD, with a low computational complexity making it easily trained with data from standard medical protocols. Precisely, EEG signals are divided into time segments for which the continuous Morlet 1-D wavelet decomposition is computed. The generalized Gaussian distribution (GGD) is fitted to the resulting coefficients and their variance and median are calculated. Next, a <i>k</i>-nearest neighbors (<i>k</i>-NN) classifier is trained to detect the spike-and-wave patterns, using the scale parameter of the GGD in addition to the variance and the median. Experiments were conducted using EEG signals from six human patients. Precisely, 106 spike-and-wave and 106 non-spike-and-wave signals were used for training, and 96 other segments for testing. The proposed SWD classification method achieved 95% sensitivity (True positive rate), 87% specificity (True Negative Rate), and 92% accuracy. These promising results set the path for new research to study the causes underlying the so-called absence epilepsy in long-term EEG recordings. |
| first_indexed | 2024-03-10T15:15:24Z |
| format | Article |
| id | doaj.art-88719ef8d0b24a24960c3b108fb37871 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T15:15:24Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-88719ef8d0b24a24960c3b108fb378712023-11-20T18:58:59ZengMDPI AGComputers2073-431X2020-10-01948510.3390/computers9040085Statistical Model-Based Classification to Detect Patient-Specific Spike-and-Wave in EEG SignalsAntonio Quintero-Rincón0Valeria Muro1Carlos D’Giano2Jorge Prendes3Hadj Batatia4Departament of Electronic, Catholic University of Argentina (UCA), Av. Alicia Moreau de Justo 1300, Buenos Aires C1107AAZ, ArgentinaFoundation for the Fight against Pediatric Neurological Disease (FLENI), Montañeses 2325, Buenos Aires C1428AQK, ArgentinaFoundation for the Fight against Pediatric Neurological Disease (FLENI), Montañeses 2325, Buenos Aires C1428AQK, ArgentinaIRIT-INPT-ENSEEIHT, University of Toulouse, 31000 Toulouse, FranceMACS School, Heriot-Watt University, Dubai Campus, Dubai Knowledge Park, Blocks 5 & 14, P.O. Box 38103, Dubai, UAESpike-and-wave discharge (SWD) pattern detection in electroencephalography (EEG) is a crucial signal processing problem in epilepsy applications. It is particularly important for overcoming time-consuming, difficult, and error-prone manual analysis of long-term EEG recordings. This paper presents a new method to detect SWD, with a low computational complexity making it easily trained with data from standard medical protocols. Precisely, EEG signals are divided into time segments for which the continuous Morlet 1-D wavelet decomposition is computed. The generalized Gaussian distribution (GGD) is fitted to the resulting coefficients and their variance and median are calculated. Next, a <i>k</i>-nearest neighbors (<i>k</i>-NN) classifier is trained to detect the spike-and-wave patterns, using the scale parameter of the GGD in addition to the variance and the median. Experiments were conducted using EEG signals from six human patients. Precisely, 106 spike-and-wave and 106 non-spike-and-wave signals were used for training, and 96 other segments for testing. The proposed SWD classification method achieved 95% sensitivity (True positive rate), 87% specificity (True Negative Rate), and 92% accuracy. These promising results set the path for new research to study the causes underlying the so-called absence epilepsy in long-term EEG recordings.https://www.mdpi.com/2073-431X/9/4/85spike-and-wavegeneralized Gaussian distributionEEGMorlet wavelet<i>k</i>-nearest neighbors classifierepilepsy |
| spellingShingle | Antonio Quintero-Rincón Valeria Muro Carlos D’Giano Jorge Prendes Hadj Batatia Statistical Model-Based Classification to Detect Patient-Specific Spike-and-Wave in EEG Signals Computers spike-and-wave generalized Gaussian distribution EEG Morlet wavelet <i>k</i>-nearest neighbors classifier epilepsy |
| title | Statistical Model-Based Classification to Detect Patient-Specific Spike-and-Wave in EEG Signals |
| title_full | Statistical Model-Based Classification to Detect Patient-Specific Spike-and-Wave in EEG Signals |
| title_fullStr | Statistical Model-Based Classification to Detect Patient-Specific Spike-and-Wave in EEG Signals |
| title_full_unstemmed | Statistical Model-Based Classification to Detect Patient-Specific Spike-and-Wave in EEG Signals |
| title_short | Statistical Model-Based Classification to Detect Patient-Specific Spike-and-Wave in EEG Signals |
| title_sort | statistical model based classification to detect patient specific spike and wave in eeg signals |
| topic | spike-and-wave generalized Gaussian distribution EEG Morlet wavelet <i>k</i>-nearest neighbors classifier epilepsy |
| url | https://www.mdpi.com/2073-431X/9/4/85 |
| work_keys_str_mv | AT antonioquinterorincon statisticalmodelbasedclassificationtodetectpatientspecificspikeandwaveineegsignals AT valeriamuro statisticalmodelbasedclassificationtodetectpatientspecificspikeandwaveineegsignals AT carlosdgiano statisticalmodelbasedclassificationtodetectpatientspecificspikeandwaveineegsignals AT jorgeprendes statisticalmodelbasedclassificationtodetectpatientspecificspikeandwaveineegsignals AT hadjbatatia statisticalmodelbasedclassificationtodetectpatientspecificspikeandwaveineegsignals |