Yan Chen

Yan Chen


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 May 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
IAIjaz Ahmad
Ijaz Ahmad
ZLZhenzhen Liu
Zhenzhen Liu
LLLin Li
Lin Li
Inam UllahInam Ullah
Inam Ullah
SASunday Timothy Aboyeji
Sunday Timothy Aboyeji
SCShixiong Chen
Shixiong Chen
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.

20 December 2024 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
SASunday Timothy Aboyeji
Sunday Timothy Aboyeji
IAIjaz Ahmad
Ijaz Ahmad
XWXin Wang
Xin Wang
YCYan Chen
Yan Chen
CYChen Yao
Chen Yao
SCShixiong Chen
Shixiong Chen

5 September 2022 in Seizure: European Journal of Epilepsy
Verified
Journal Article
Open access
LLLin Li
Lin Li
SLSufang Lin
Sufang Lin
ZTZeshi Tan
Zeshi Tan
LCLi Chen
Li Chen
QZQi Zeng
Qi Zeng
YCYan Chen
Yan Chen
It has been suggested that asymmetric hypsarrhythmia is associated with structural etiology. We devised the Hypsarrhythmic Asymmetric Scoring Scheme (HASS) to quantify the degree of hypsarrhythmic asymmetry in a retrospective series of patients who underwent surgical treatment at our center. The present study aimed to investigate the role of HASS in predicting the postsurgical seizure outcomes. We retrospectively analyzed the records of 46 children with hypsarrhythmia who underwent resective epilepsy surgery between 2018 and 2020 and were followed up for at least 1 year after surgery. Hypsarrhythmia severity in each hemisphere was quantified and scored. The HASS score was calculated as the difference between the two hemispheres. Univariate results were submitted to logistic regression models to identify independent predictors for favorable surgical outcomes. Of the 46 patients who underwent resective surgery, Engel's class I-Ⅱ outcomes were achieved in 34 (73.9%). The Engel I-Ⅱ group had a significantly higher HASS score than the Engel Ⅲ-Ⅳ group (p<0.001). Multivariate analysis showed that the HASS score was the only significant predictor of good outcomes (p = 0.011). Further receiver operating characteristic analysis showed that a threshold of 7 yielded a better seizure outcome with a sensitivity of 97.06% and specificity of 83.33%. As the first hypsarrhythmia scoring system specially designed for presurgical evaluation, the HASS score may contribute to predicting the postsurgical seizure outcome from the electroencephalography perspective.

1 October 2024 in Journal of Neural Engineering
Verified
Journal Article
Closed access
SASunday Timothy Aboyeji
Sunday Timothy Aboyeji
XWXin Wang
Xin Wang
YCYan Chen
Yan Chen
IAIjaz Ahmad
Ijaz Ahmad
LLLin Li
Lin Li
SCShixiong Chen
Shixiong Chen
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.

8 April 2022 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
ZLZhenzhen Liu
Zhenzhen Liu
XWXin Wang
Xin Wang
MZMingxing Zhu
Mingxing Zhu
YHYuchao He
Yuchao He
LLLin Li
Lin Li
GLGuanglin Li
Guanglin Li
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.

31 December 2025 in Bioengineering
Verified
Journal Article
Open access
PDF file
JFJunyuan Feng
Junyuan Feng
ZLZhenzhen Liu
Zhenzhen Liu
Linlin ShenLinlin Shen
Linlin Shen
XLXiaoling Luo
Xiaoling Luo
YCYan Chen
Yan Chen
TZTian Zhang
Tian Zhang
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.