Yan Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yan Chen has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Shixiong Chen
School of Medicine, The Chinese University of Hong Kong, Shenzhen, China
6 shared publications - Xin Wang
Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
6 shared publications - Guanglin Li
Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
5 shared publications - Lin Li
Surgery Division, Epilepsy Center, Shenzhen Childrens Hospital, Shenzhen, China
5 shared publications - Ijaz Ahmad
Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture, Peshawar 25130, Pakistan
4 shared publications - Sunday Timothy Aboyeji
School of Medicine, The Chinese University of Hong Kong, Shenzhen, China
4 shared publications
Latest Publications
- Open Access
- 24 June 2026
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 26 (1)
SinTransNet: an EEG-based deep learning framework for infantile epileptic spasms syndrome detection
Infantile Epileptic Spasms Syndrome (IESS) represents a severe form of developmental epileptic encephalopathy in infancy, characterized by clusters of spasms and hypsarrhythmia patterns on electroencephalogram (EEG), which often lead to long-term neurodevelopmental impairments if not diagnosed promptly. The inherent non-stationarity and polymorphic complexity of EEG signals complicate interpretation, resulting in time-consuming and error-prone diagnostics that hinder timely therapeutic interventions. To address these challenges, we propose SinTransNet, an innovative EEG-based deep learning framework that combines multi-band signal decomposition, adaptive sinusoidal convolutions, and Transformer-based attention mechanism. This architecture decomposes EEG into five key frequency bands (δ, θ, α, β, γ) to isolate oscillatory features such as spike-and-wave complexes, employs sinusoidal convolutions for frequency-adaptive feature extraction, and utilizes Transformer attention to capture inter-band correlations and long-range dependencies essential for accurate IESS detection. Evaluated on a proprietary dataset comprising 129 EEG recordings with 1,941 epileptic spasm events, SinTransNet demonstrates superior performance with average accuracy of 85.69%, sensitivity of 80.55%, and specificity of 90.76%. By providing an automated, efficient tool for IESS identification, SinTransNet holds promise for enhancing clinical workflows and supporting early interventions in pediatric neurology.
- 24 June 2026
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 26 (1)
Open AccessSinTransNet: an EEG-based deep learning framework for infantile epileptic spasms syndrome detection
Infantile Epileptic Spasms Syndrome (IESS) represents a severe form of developmental epileptic encephalopathy in infancy, characterized by clusters of spasms and hypsarrhythmia patterns on electroencephalogram (EEG), which often lead to long-term neurodevelopmental impairments if not diagnosed promptly. The inherent non-stationarity and polymorphic complexity of EEG signals complicate interpretation, resulting in time-consuming and error-prone diagnostics that hinder timely therapeutic interventions. To address these challenges, we propose SinTransNet, an innovative EEG-based deep learning framework that combines multi-band signal decomposition, adaptive sinusoidal convolutions, and Transformer-based attention mechanism. This architecture decomposes EEG into five key frequency bands (δ, θ, α, β, γ) to isolate oscillatory features such as spike-and-wave complexes, employs sinusoidal convolutions for frequency-adaptive feature extraction, and utilizes Transformer attention to capture inter-band correlations and long-range dependencies essential for accurate IESS detection. Evaluated on a proprietary dataset comprising 129 EEG recordings with 1,941 epileptic spasm events, SinTransNet demonstrates superior performance with average accuracy of 85.69%, sensitivity of 80.55%, and specificity of 90.76%. By providing an automated, efficient tool for IESS identification, SinTransNet holds promise for enhancing clinical workflows and supporting early interventions in pediatric neurology.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-12
WGB-GLFI: A Novel Graph-Based Global-Local Feature Interaction Framework for Automated Seizure Detection
Epilepsy detection faces significant challenges due to unpredictable seizures, ranging from brief awareness lapses to severe convulsions, posing risks to patients' safety and quality of life. In recent years, deep learning has become a mainstream approach in this field, leveraging advanced computational resources and EEG datasets. However, a key challenge remains: existing methods often lack unified spatial modeling and struggle to effectively handle local detailed features, thereby limiting their accuracy and robustness. To address these issues, we propose the Weighted Graph Building Global-Local Feature Interaction (WGB-GLFI) framework, which integrates spatial connectivity and dynamic patterns through a Weighted Graph Building (WGB) module and a Global-Local Feature Interaction (GLFI) module. This approach excels by comprehensively capturing the dynamic spatial relationships during epileptic seizures and achieving seamless global-local feature integration, significantly enhancing seizure detection performance. Its effectiveness has been validated across multiple datasets, including CHB-MIT, Siena Scalp, and private datasets, demonstrating robust and reliable results. Evaluated on these datasets, our model achieves accuracy rates of 99.28%, 99.21%, and 99.30%, respectively. The reliability and robustness of our framework provide epilepsy patients with faster and more reliable seizure detection, which helps to intervene in a timely manner and improve the quality of life of patients.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-12
WGB-GLFI: A Novel Graph-Based Global-Local Feature Interaction Framework for Automated Seizure Detection
Epilepsy detection faces significant challenges due to unpredictable seizures, ranging from brief awareness lapses to severe convulsions, posing risks to patients' safety and quality of life. In recent years, deep learning has become a mainstream approach in this field, leveraging advanced computational resources and EEG datasets. However, a key challenge remains: existing methods often lack unified spatial modeling and struggle to effectively handle local detailed features, thereby limiting their accuracy and robustness. To address these issues, we propose the Weighted Graph Building Global-Local Feature Interaction (WGB-GLFI) framework, which integrates spatial connectivity and dynamic patterns through a Weighted Graph Building (WGB) module and a Global-Local Feature Interaction (GLFI) module. This approach excels by comprehensively capturing the dynamic spatial relationships during epileptic seizures and achieving seamless global-local feature integration, significantly enhancing seizure detection performance. Its effectiveness has been validated across multiple datasets, including CHB-MIT, Siena Scalp, and private datasets, demonstrating robust and reliable results. Evaluated on these datasets, our model achieves accuracy rates of 99.28%, 99.21%, and 99.30%, respectively. The reliability and robustness of our framework provide epilepsy patients with faster and more reliable seizure detection, which helps to intervene in a timely manner and improve the quality of life of patients.
- 18 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 56 (2) , 331-342
A Novel Hybrid Feature Selection Technique for Epileptic Seizure Classification
Patients with epilepsy experience significant neurological impairments due to abnormal electrical activities in their brains, impacting daily activities. Computer-aided diagnosis systems can assist neurologists in managing patients with this disease. Moreover, feature extraction has been proposed to be an integral part of the classification process. However, training machine learning (ML) models with multiple features from multichannel electroencephalogram (EEG) signals is computationally demanding. Feature selection (FS) minimizes the system’s computational cost by identifying deterministic features. However, individual FS techniques often show unstable performance across EEG datasets. Therefore, this study proposed a hybrid FS technique with a Random Forest Bayesian optimization classifier to dynamically select relevant features that improve ML performance across EEG datasets. Initially, the Bonn, CHB-MIT, and TUH EEG datasets were segmented into 1-s epochs with an overlap of 0.75. Relevant features are obtained through a hybrid of ANOVA, correlation, and graph-based FS techniques. Mean decrease impurity and meta-model were used to evaluate feature importance and ranking. RF-BO was used to predict the outcome of each FS technique for relevant cases of the Bonn, CHB-MIT, and TUH datasets after subject-level splitting with holdout. An average accuracy of 98.93% and 95.91% was obtained for the Bonn dataset’s binary and ternary classification cases, respectively. In addition, accuracies of 96.51% and 91.71%, respectively, obtained for the binary case of CHB-MIT and the multiclass case of TUH datasets with 60 features are better than those in previous studies, making the proposed model effective for seizure classifications.
- 18 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 56 (2) , 331-342
A Novel Hybrid Feature Selection Technique for Epileptic Seizure Classification
Patients with epilepsy experience significant neurological impairments due to abnormal electrical activities in their brains, impacting daily activities. Computer-aided diagnosis systems can assist neurologists in managing patients with this disease. Moreover, feature extraction has been proposed to be an integral part of the classification process. However, training machine learning (ML) models with multiple features from multichannel electroencephalogram (EEG) signals is computationally demanding. Feature selection (FS) minimizes the system’s computational cost by identifying deterministic features. However, individual FS techniques often show unstable performance across EEG datasets. Therefore, this study proposed a hybrid FS technique with a Random Forest Bayesian optimization classifier to dynamically select relevant features that improve ML performance across EEG datasets. Initially, the Bonn, CHB-MIT, and TUH EEG datasets were segmented into 1-s epochs with an overlap of 0.75. Relevant features are obtained through a hybrid of ANOVA, correlation, and graph-based FS techniques. Mean decrease impurity and meta-model were used to evaluate feature importance and ranking. RF-BO was used to predict the outcome of each FS technique for relevant cases of the Bonn, CHB-MIT, and TUH datasets after subject-level splitting with holdout. An average accuracy of 98.93% and 95.91% was obtained for the Bonn dataset’s binary and ternary classification cases, respectively. In addition, accuracies of 96.51% and 91.71%, respectively, obtained for the binary case of CHB-MIT and the multiclass case of TUH datasets with 60 features are better than those in previous studies, making the proposed model effective for seizure classifications.
- Open Access
- 31 December 2025
- Published by MDPI AG in Bioengineering
- Vol. 13 (1) , 57
IESS-FusionNet: Physiologically Inspired EEG-EMG Fusion with Linear Recurrent Attention for Infantile Epileptic Spasms Syndrome Detection
Infantile Epileptic Spasms Syndrome (IESS) is a devastating epileptic encephalopathy of infancy that carries a high risk of lifelong neurodevelopmental disability. Timely diagnosis is critical, as every week of delay in effective treatment is associated with worse cognitive outcomes. Although synchronized electroencephalogram (EEG) and surface electromyography (EMG) recordings capture both the electrophysiological and motor signatures of spasms, accurate automated detection remains challenging due to the non-stationary nature of the signals and the absence of physiologically plausible inter-modal fusion in current deep learning approaches. We introduce IESS-FusionNet, an end-to-end dual-stream framework specifically designed for accurate, real-time IESS detection from simultaneous EEG and EMG. Each modality is processed by a dedicated Unimodal Encoder that hierarchically integrates Continuous Wavelet Transform, Spatio-Temporal Convolution, and Bidirectional Mamba to efficiently extract frequency-specific, spatially structured, local and long-range temporal features within a compact module. A novel Cross Time-Mixing module, built upon the linear recurrent attention of the Receptance Weighted Key Value (RWKV) architecture, subsequently performs efficient, time-decaying, bidirectional cross-modal integration that explicitly respects the causal and physiological properties of cortico-muscular coupling during spasms. Evaluated on an in-house clinical dataset of synchronized EEG-EMG recordings from infants with confirmed IESS, IESS-FusionNet achieves 89.5% accuracy, 90.7% specificity, and 88.3% sensitivity, significantly outperforming recent unimodal and multimodal baselines. Comprehensive ablation studies validate the contribution of each component, while the proposed cross-modal fusion requires approximately 60% fewer parameters than equivalent quadratic cross-attention mechanisms, making it suitable for real-time clinical deployment. IESS-FusionNet delivers an accurate, computationally efficient solution with physiologically inspired cross-modal fusion for the automated detection of infantile epileptic spasms, offering promise for future clinical applications in reducing diagnostic delay.
- 31 December 2025
- Published by MDPI AG in Bioengineering
- Vol. 13 (1) , 57
Open AccessIESS-FusionNet: Physiologically Inspired EEG-EMG Fusion with Linear Recurrent Attention for Infantile Epileptic Spasms Syndrome Detection
Infantile Epileptic Spasms Syndrome (IESS) is a devastating epileptic encephalopathy of infancy that carries a high risk of lifelong neurodevelopmental disability. Timely diagnosis is critical, as every week of delay in effective treatment is associated with worse cognitive outcomes. Although synchronized electroencephalogram (EEG) and surface electromyography (EMG) recordings capture both the electrophysiological and motor signatures of spasms, accurate automated detection remains challenging due to the non-stationary nature of the signals and the absence of physiologically plausible inter-modal fusion in current deep learning approaches. We introduce IESS-FusionNet, an end-to-end dual-stream framework specifically designed for accurate, real-time IESS detection from simultaneous EEG and EMG. Each modality is processed by a dedicated Unimodal Encoder that hierarchically integrates Continuous Wavelet Transform, Spatio-Temporal Convolution, and Bidirectional Mamba to efficiently extract frequency-specific, spatially structured, local and long-range temporal features within a compact module. A novel Cross Time-Mixing module, built upon the linear recurrent attention of the Receptance Weighted Key Value (RWKV) architecture, subsequently performs efficient, time-decaying, bidirectional cross-modal integration that explicitly respects the causal and physiological properties of cortico-muscular coupling during spasms. Evaluated on an in-house clinical dataset of synchronized EEG-EMG recordings from infants with confirmed IESS, IESS-FusionNet achieves 89.5% accuracy, 90.7% specificity, and 88.3% sensitivity, significantly outperforming recent unimodal and multimodal baselines. Comprehensive ablation studies validate the contribution of each component, while the proposed cross-modal fusion requires approximately 60% fewer parameters than equivalent quadratic cross-attention mechanisms, making it suitable for real-time clinical deployment. IESS-FusionNet delivers an accurate, computationally efficient solution with physiologically inspired cross-modal fusion for the automated detection of infantile epileptic spasms, offering promise for future clinical applications in reducing diagnostic delay.
- Open Access
- 26 November 2025
- Published by Springer Nature in Research Square
Cognitive Impairments and Neurofunctional Alterations in Children with ESES: Insights from WISC-IV and Resting-State fMRI
Background Electrical Status Epilepticus During Sleep (ESES) is a rare pediatric epilepsy syndrome characterized by sleep-induced epileptiform discharges, leading to cognitive and behavioral impairments. We aimed to investigate the underlying neural mechanisms that are critical for advancing early diagnosis and targeted interventions. Methods Twenty-five children with ESES and 30 age- and sex-matched healthy controls were enrolled. Cognitive function was assessed via the Wechsler Intelligence Scale for Children, Fourth Edition (WISC-IV), focusing on Full-Scale IQ (FSIQ), Verbal Comprehension Index (VCI), Perceptual Reasoning Index (PRI), Working Memory Index (WMI), and Processing Speed Index (PSI). Resting-state functional MRI (rs-fMRI) was conducted to evaluate neural activity via regional homogeneity (ReHo) analysis. Correlations between ReHo values and cognitive scores were analyzed in the ESES group. Results Compared with healthy controls, children with ESES presented significantly lower FSIQ and PRI scores (P = 0.017, P = 0.016), indicating cognitive impairments in global intellectual abilities and perceptual reasoning. rs-fMRI revealed decreased ReHo in the left Superior Frontal Gyrus (premotor area), bilateral postcentral gyri (primary somatosensory cortex), right cerebellum posterior, and rolandic operculum. In contrast, increased ReHo was observed in the left precuneus and left middle frontal gyrus. ReHo in the right postcentral gyrus showed a positive correlation with FSIQ and VCI scores (r = 0.56, P = 0.01; r = 0.67, P < 0.001). Conclusions ESES is associated with significant cognitive deficits, particularly in perceptual reasoning and verbal comprehension, alongside altered neural activity patterns. ReHo analysis revealed changes in local neural activity within key brain regions linked to cognitive function. These findings highlight the potential of rs-fMRI metrics as biomarkers for assessing cognitive impairments and guiding therapeutic interventions in ESES.
- 26 November 2025
- Published by Springer Nature in Research Square
Open AccessCognitive Impairments and Neurofunctional Alterations in Children with ESES: Insights from WISC-IV and Resting-State fMRI
Background Electrical Status Epilepticus During Sleep (ESES) is a rare pediatric epilepsy syndrome characterized by sleep-induced epileptiform discharges, leading to cognitive and behavioral impairments. We aimed to investigate the underlying neural mechanisms that are critical for advancing early diagnosis and targeted interventions. Methods Twenty-five children with ESES and 30 age- and sex-matched healthy controls were enrolled. Cognitive function was assessed via the Wechsler Intelligence Scale for Children, Fourth Edition (WISC-IV), focusing on Full-Scale IQ (FSIQ), Verbal Comprehension Index (VCI), Perceptual Reasoning Index (PRI), Working Memory Index (WMI), and Processing Speed Index (PSI). Resting-state functional MRI (rs-fMRI) was conducted to evaluate neural activity via regional homogeneity (ReHo) analysis. Correlations between ReHo values and cognitive scores were analyzed in the ESES group. Results Compared with healthy controls, children with ESES presented significantly lower FSIQ and PRI scores (P = 0.017, P = 0.016), indicating cognitive impairments in global intellectual abilities and perceptual reasoning. rs-fMRI revealed decreased ReHo in the left Superior Frontal Gyrus (premotor area), bilateral postcentral gyri (primary somatosensory cortex), right cerebellum posterior, and rolandic operculum. In contrast, increased ReHo was observed in the left precuneus and left middle frontal gyrus. ReHo in the right postcentral gyrus showed a positive correlation with FSIQ and VCI scores (r = 0.56, P = 0.01; r = 0.67, P < 0.001). Conclusions ESES is associated with significant cognitive deficits, particularly in perceptual reasoning and verbal comprehension, alongside altered neural activity patterns. ReHo analysis revealed changes in local neural activity within key brain regions linked to cognitive function. These findings highlight the potential of rs-fMRI metrics as biomarkers for assessing cognitive impairments and guiding therapeutic interventions in ESES.
- 20 December 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 185, 109558
DCSENets: Interpretable deep learning for patient-independent seizure classification using enhanced EEG-based spectrogram visualization
- 20 December 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 185, 109558
DCSENets: Interpretable deep learning for patient-independent seizure classification using enhanced EEG-based spectrogram visualization
- 1 October 2024
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 21 (5) , 056040
Automatic detection of epileptic seizure based on one dimensional cascaded convolutional autoencoder with adaptive window-thresholding
Objective. Identifying the seizure occurrence period (SOP) in extended EEG recordings is crucial for neurologists to diagnose seizures effectively. However, many existing computer-aided diagnosis systems for epileptic seizure detection (ESD) primarily focus on distinguishing between ictal and interictal states in EEG recordings. This focus has limited their application in clinical settings, as these systems typically rely on supervised learning approaches that require labeled data. Approach. To address this, our study introduces an unsupervised learning framework for ESD using a 1D- cascaded convolutional autoencoder (1D-CasCAE). In this approach, EEG recordings from selected patients in the CHB-MIT datasets are first segmented into 5 s epochs. Eight informative channels are chosen based on the correlation coefficient and Shannon entropy. The 1D-CasCAE is designed to autonomously learn the characteristic patterns of interictal (non-seizure) segments through downsampling and upsampling processes. The integration of adaptive thresholding and a moving window significantly enhances the model’s robustness, enabling it to accurately identify ictal segments in long EEG recordings. Main results. Experimental results demonstrate that the proposed 1D-CasCAE effectively learns normal EEG signal patterns and efficiently detects anomalies (ictal segments) using reconstruction errors. When compared with other leading methods in anomaly detection, our model exhibits superior performance, as evidenced by its average Gmean, sensitivity, specificity, precision, and false positive rate scores of 98.00% ± 3.51%, 94.94% ± 6.92%, 99.60% ± 0.30%, 79.92% ± 13.56% and 0.0044 ± 0.0030 h−1 respectively for a typical patient in CHB-MIT datasets. Significance. The developed model framework can be employed in clinical settings, replacing the manual inspection process of EEG signals by neurologists. Furthermore, the proposed automated system can adapt to each patient’s SOP through the use of variable time windows for seizure detection.
- 1 October 2024
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 21 (5) , 056040
Automatic detection of epileptic seizure based on one dimensional cascaded convolutional autoencoder with adaptive window-thresholding
Objective. Identifying the seizure occurrence period (SOP) in extended EEG recordings is crucial for neurologists to diagnose seizures effectively. However, many existing computer-aided diagnosis systems for epileptic seizure detection (ESD) primarily focus on distinguishing between ictal and interictal states in EEG recordings. This focus has limited their application in clinical settings, as these systems typically rely on supervised learning approaches that require labeled data. Approach. To address this, our study introduces an unsupervised learning framework for ESD using a 1D- cascaded convolutional autoencoder (1D-CasCAE). In this approach, EEG recordings from selected patients in the CHB-MIT datasets are first segmented into 5 s epochs. Eight informative channels are chosen based on the correlation coefficient and Shannon entropy. The 1D-CasCAE is designed to autonomously learn the characteristic patterns of interictal (non-seizure) segments through downsampling and upsampling processes. The integration of adaptive thresholding and a moving window significantly enhances the model’s robustness, enabling it to accurately identify ictal segments in long EEG recordings. Main results. Experimental results demonstrate that the proposed 1D-CasCAE effectively learns normal EEG signal patterns and efficiently detects anomalies (ictal segments) using reconstruction errors. When compared with other leading methods in anomaly detection, our model exhibits superior performance, as evidenced by its average Gmean, sensitivity, specificity, precision, and false positive rate scores of 98.00% ± 3.51%, 94.94% ± 6.92%, 99.60% ± 0.30%, 79.92% ± 13.56% and 0.0044 ± 0.0030 h−1 respectively for a typical patient in CHB-MIT datasets. Significance. The developed model framework can be employed in clinical settings, replacing the manual inspection process of EEG signals by neurologists. Furthermore, the proposed automated system can adapt to each patient’s SOP through the use of variable time windows for seizure detection.
- Top Cited Papers
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (10) , 5742-5754
Robust Epileptic Seizure Detection Based on Biomedical Signals Using an Advanced Multi-View Deep Feature Learning Approach
Epilepsy is a neurological disorder characterized by abnormal neuronal discharges that manifest in life-threatening seizures. These are often monitored via EEG signals, a key aspect of biomedical signal processing (BSP). Accurate epileptic seizure (ES) detection significantly depends on the precise identification of key EEG features, which requires a deep understanding of the data's intrinsic domain. Therefore, this study presents an Advanced Multi-View Deep Feature Learning (AMV-DFL) framework based on machine learning (ML) technology to enhance the detection of relevant EEG signal features for ES. Our method initially applies a fast Fourier transform (FFT) to EEG data for traditional frequency domain feature (TFD-F) extraction and directly incorporates time domain (TD) features from the raw EEG signals, establishing a comprehensive traditional multi-view feature (TMV-F). Deep features are subsequently extracted autonomously from optimal layers of one-dimensional convolutional neural networks (1D CNN), resulting in multi-view deep features (MV-DF) integrating both time and frequency domains. A multi-view forest (MV-F) is an interpretable rule-based advanced ML classifier used to construct a robust, generalized classification. Tree-based SHAP explainable artificial intelligence (T-XAI) is incorporated for interpreting and explaining the underlying rules. Experimental results confirm our method's superiority, surpassing models using TMV-FL and single-view deep features (SV-DF) by 4% and outperforming other state-of-the-art methods by an average of 3% in classification accuracy. The AMV-DFL approach aids clinicians in identifying EEG features indicative of ES, potentially discovering novel biomarkers, and improving diagnostic capabilities in epilepsy management.
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (10) , 5742-5754
Top Cited PapersRobust Epileptic Seizure Detection Based on Biomedical Signals Using an Advanced Multi-View Deep Feature Learning Approach
Epilepsy is a neurological disorder characterized by abnormal neuronal discharges that manifest in life-threatening seizures. These are often monitored via EEG signals, a key aspect of biomedical signal processing (BSP). Accurate epileptic seizure (ES) detection significantly depends on the precise identification of key EEG features, which requires a deep understanding of the data's intrinsic domain. Therefore, this study presents an Advanced Multi-View Deep Feature Learning (AMV-DFL) framework based on machine learning (ML) technology to enhance the detection of relevant EEG signal features for ES. Our method initially applies a fast Fourier transform (FFT) to EEG data for traditional frequency domain feature (TFD-F) extraction and directly incorporates time domain (TD) features from the raw EEG signals, establishing a comprehensive traditional multi-view feature (TMV-F). Deep features are subsequently extracted autonomously from optimal layers of one-dimensional convolutional neural networks (1D CNN), resulting in multi-view deep features (MV-DF) integrating both time and frequency domains. A multi-view forest (MV-F) is an interpretable rule-based advanced ML classifier used to construct a robust, generalized classification. Tree-based SHAP explainable artificial intelligence (T-XAI) is incorporated for interpreting and explaining the underlying rules. Experimental results confirm our method's superiority, surpassing models using TMV-FL and single-view deep features (SV-DF) by 4% and outperforming other state-of-the-art methods by an average of 3% in classification accuracy. The AMV-DFL approach aids clinicians in identifying EEG features indicative of ES, potentially discovering novel biomarkers, and improving diagnostic capabilities in epilepsy management.
- Open Access
- 5 September 2022
- Published by Elsevier in Seizure: European Journal of Epilepsy
- Vol. 101, 205-210
Resective epilepsy surgery for West syndrome: The Hypsarrhythmic Asymmetric Scoring Scheme is a determining predictor of seizure outcome
- 5 September 2022
- Published by Elsevier in Seizure: European Journal of Epilepsy
- Vol. 101, 205-210
Open AccessResective epilepsy surgery for West syndrome: The Hypsarrhythmic Asymmetric Scoring Scheme is a determining predictor of seizure outcome
- Open Access
- 8 April 2022
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2022, 1-11
The Effects of Different Reference Methods on Decision-Making Implications of Auditory Brainstem Response
Hearing loss is a common disease affecting public health all around the world. In clinic, auditory brainstem response (ABR) has been widely used for the detection of hearing loss based on its convenience and accuracy. The different reference methods directly influence the quality of the ABR waveform which in turn affects the ABR-based diagnosis. Therefore, in this study, a reference electrode standardization technique (REST) was adopted to systematically investigate and evaluate the effect of different reference methods on the quality of ABR waveform in comparison with the conventional average reference (AR) and mean mastoid (MM) methods. In this study, ABR signals induced by click stimulus were acquired via an EEG electrode cap arrays, and those located on the six channels along the midline were compared systemically. The results showed that, when considering the different channels, the ABR in the Cz channel showed the best morphology. Then, the ABR waveforms acquired via the REST method possessed better morphologies with large amplitude ( μV for wave I, μV for wave III, and μV for wave V) when compared with the traditional method. Summarily, we found that the REST and MM methods improved the quality of ABR on both amplitude and morphology under different stimulation rates and levels without changing the latencies of ABR when compared with the conventional AR method, suggesting that the REST and MM methods have the potential to help physicians with high accurate ABR-based clinical diagnosis. Moreover, this study might also provide a theoretic basis of reference methods on the acquisition of electroencephalogram over public health issues.
- 8 April 2022
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2022, 1-11
Open AccessThe Effects of Different Reference Methods on Decision-Making Implications of Auditory Brainstem Response
Hearing loss is a common disease affecting public health all around the world. In clinic, auditory brainstem response (ABR) has been widely used for the detection of hearing loss based on its convenience and accuracy. The different reference methods directly influence the quality of the ABR waveform which in turn affects the ABR-based diagnosis. Therefore, in this study, a reference electrode standardization technique (REST) was adopted to systematically investigate and evaluate the effect of different reference methods on the quality of ABR waveform in comparison with the conventional average reference (AR) and mean mastoid (MM) methods. In this study, ABR signals induced by click stimulus were acquired via an EEG electrode cap arrays, and those located on the six channels along the midline were compared systemically. The results showed that, when considering the different channels, the ABR in the Cz channel showed the best morphology. Then, the ABR waveforms acquired via the REST method possessed better morphologies with large amplitude ( μV for wave I, μV for wave III, and μV for wave V) when compared with the traditional method. Summarily, we found that the REST and MM methods improved the quality of ABR on both amplitude and morphology under different stimulation rates and levels without changing the latencies of ABR when compared with the conventional AR method, suggesting that the REST and MM methods have the potential to help physicians with high accurate ABR-based clinical diagnosis. Moreover, this study might also provide a theoretic basis of reference methods on the acquisition of electroencephalogram over public health issues.