Background Epilepsy is a common chronic neurological disease.Its repeated seizure attacks have a great negative impact on patients’physical and mental health.The diagnosis of epilepsy mainly depends on electroencepha...Background Epilepsy is a common chronic neurological disease.Its repeated seizure attacks have a great negative impact on patients’physical and mental health.The diagnosis of epilepsy mainly depends on electroencephalogram(EEG)signals detection and analysis.There are two main EEG signals detection methods for epilepsy.One is the detection based on abnormal waveform,the other is the analysis of EEG signals based on the traditional machine learning.The feature extraction method of the traditional machine learning is difcult to capture the high-dimension information between adjacent sequences.Methods In this paper,redundant information was removed from the data by Gaussian fltering,downsampling,and short-time Fourier transform.Convolutional Neural Networks(CNN)was used to extract the high-dimensional features of the preprocessed data,and then Gate Recurrent Unit(GRU)was used to combine the sequence information before and after,to fully integrate the adjacent information EEG signals and improve the accuracy of the model detection.Results Four models were designed and compared.The experimental results showed that the prediction model based on deep residual network and bidirectional GRU had the best efect,and the test accuracy of the absence epilepsy test set reached 92%.Conclusions The prediction time of the network is only 10 sec when predicting four-hour EEG signals.It can be efectively used in EEG software to provide reference for doctors in EEG analysis and save doctors’time,which has great practical value.展开更多
基金Construction and application demonstration of an intelligent diagnosis and treatment system for children’s diseases based on a smart medical platform(202102AA100021)The study is approved by the Ethics Committee of Afliated Hospital of Kunming Children’s Hospital,and participants gave informed consent(2021-03-333-K01).
文摘Background Epilepsy is a common chronic neurological disease.Its repeated seizure attacks have a great negative impact on patients’physical and mental health.The diagnosis of epilepsy mainly depends on electroencephalogram(EEG)signals detection and analysis.There are two main EEG signals detection methods for epilepsy.One is the detection based on abnormal waveform,the other is the analysis of EEG signals based on the traditional machine learning.The feature extraction method of the traditional machine learning is difcult to capture the high-dimension information between adjacent sequences.Methods In this paper,redundant information was removed from the data by Gaussian fltering,downsampling,and short-time Fourier transform.Convolutional Neural Networks(CNN)was used to extract the high-dimensional features of the preprocessed data,and then Gate Recurrent Unit(GRU)was used to combine the sequence information before and after,to fully integrate the adjacent information EEG signals and improve the accuracy of the model detection.Results Four models were designed and compared.The experimental results showed that the prediction model based on deep residual network and bidirectional GRU had the best efect,and the test accuracy of the absence epilepsy test set reached 92%.Conclusions The prediction time of the network is only 10 sec when predicting four-hour EEG signals.It can be efectively used in EEG software to provide reference for doctors in EEG analysis and save doctors’time,which has great practical value.
