What is the clinical evidence from this study?

Study design: Other. Population: Epilepsy (n=500). Intervention: WBCKNN classifier vs. Traditional classifiers (kNN, SVM, DT, RF, XG-boost, DNN). Primary outcome: Classification accuracy.

January 1, 2020Open Access

An Improved kNN Classifier for Epilepsy Diagnosis

ZWZhiping WangXuzhou Medical College JNJunying NaDalian Maritime University BZBaoyou ZhengDalian Maritime University

Key Result

The WBCKNN classifier achieved a maximum classification accuracy of 99.67% for two-class and 99.0% for three-class epilepsy detection problems, outperforming traditional machine learning models.

Structured PICO

Does the WBCKNN classifier improve the accuracy of epilepsy detection from EEG signals compared to traditional classifiers?

Population

500 single-channel EEG segments from 5 healthy volunteers and 5 epileptic patients used to evaluate an automated epilepsy diagnosis algorithm.

Intervention

Weighted k-nearest neighbor classifier based on Bray Curtis distance (WBCKNN) with Fourier transform preprocessing

Comparator

Traditional machine learning classifiers including kNN, SVM, Decision Tree (DT), Random Forest (RF), XG-boost, and Deep Neural Network (DNN)

Outcome

Classification accuracy, sensitivity, specificity, and false alarm rate

The proposed WBCKNN classifier with Fourier transform preprocessing achieves high accuracy in detecting epileptic seizures from EEG signals, outperforming traditional machine learning models.

Abstract

The electroencephalogram (EEG) signals are important for reflecting seizures and the diagnosis of epilepsy. In this paper, a weighted k-nearest neighbor classifier based on Bray Curtis distance (WBCKNN) is proposed to implement automatic detection of epilepsy. The Fourier transform can transform the time-domain characteristics of the signal into frequency domain, which can display more useful information. The WBCKNN classifier can well overcome the sensitivity of the neighborhood size k and has good robustness. Therefore, it can classify EEG signals more accurately for different situations. WBCKNN is applied on public dataset and tested by k-fold cross-validation. Experimental results show that the best accuracy of the two-classification problems and three-classification problems is 99.67% and 99%, respectively. Compared to other classifiers, the accuracy of classification is also improved. In addition, this method is superior to traditional methods in sensitivity, specificity and false alarm rate of epilepsy classification. This method can be applied to the medical market to help doctors diagnose epilepsy.

Ask AI

Helpful

Bookmark

View Full Paper