Huan Yu

Dr. Huan Yu


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
22 September 2017 in SLEEP
Verified
Journal Article
Closed access
PDF file
CFCong Fu
Cong Fu
NZNa Zhao
Na Zhao
ZLZhen Liu
Zhen Liu
LYLu-Hua Yuan
Lu-Hua Yuan
CXChen Xie
Chen Xie
YCYunfei Chen
Yunfei Chen
To evaluate the short-term efficacy of acupuncture for the treatment of peri-menopausal insomnia (PMI). Design: A randomized, participant-blind, placebo-controlled trial consisted of the acupuncture group (n = 38) and placebo-acupuncture group (n = 38). Setting: A tertiary teaching and general hospital. Participants: 76 peri-menopausal women with insomnia disorder based on the International Classification of Sleep Disorders, Third Edition. Interventions: A 10-session of acupuncture at bilateral Shenshu (BL 23) and Ganshu (BL 18) with unilateral Qimen (LR 14) and Jingmen (GB 25) or Streitberger needles at the same acupoints was performed for over 3 weeks. Measurements: Pittsburgh Sleep Quality Index (PSQI) and Insomnia Severity Index (ISI) with over-night polysomnography (PSG) exam were completed at baseline and post-treatment. After the treatments, the decrease from baseline in PSQI score was 8.03 points in acupuncture group and 1.29 points in placebo-acupuncture group. The change from baseline in ISI score was 11.35 points in acupuncture group and 2.87 points in placebo-acupuncture group. In PSG data, acupuncture significantly improved the sleep efficiency and total sleep time, associated with less wake after sleep onset and lower percent stage 1 after the treatment. No significant differences from baseline to post-treatment were found in placebo-acupuncture group. Acupuncture can contribute to a clinically relevant improvement in the short-term treatment of PMI, both subjectively and objectively. Acupuncture for peri-menopause insomnia: a randomized controlled trial, http://www.chictr.org.cn/showproj.aspx?proj=12118 ChiCTR-IPR-15007199, China.

9 February 2023 in npj Parkinson's Disease
Verified
Journal Article
Open access
PDF file
YTYilin Tang
Yilin Tang
LHLinlin Han
Linlin Han
SLShiyu Li
Shiyu Li
THTianyu Hu
Tianyu Hu
ZXZhiheng Xu
Zhiheng Xu
Jian WangJian Wang
Jian Wang
Glial fibrillary acidic protein (GFAP) has been suggested as a biomarker for reactive astrogliosis. We measured the levels of plasma GFAP by Simoa in 60 patients with PD with normal cognition, 63 with mild cognitive impairment (PD-MCI), 24 with dementia (PDD) and 15 healthy controls. A subgroup of patients with PD-MCI (n = 31) was followed up for 4.1 ± 2.3 years. Compared with healthy controls, plasma GFAP levels were elevated in patients with PDD (adjusted P < 0.001) and PD-MCI (adjusted P = 0.013) and were negatively correlated with the Mini Mental State Examination (MMSE) score in PD participants. Plasma GFAP predicted MCI-to-dementia conversion with an AUC of 0.90, higher than NfL, Tau and pTau181. Our results support that plasma GFAP has potential value for distinguishing patients with PDD, and predicting MCI-to-dementia conversion in PD.

7 March 2023 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
HYHaun Yu
Haun Yu
WZWei Zhou
Wei Zhou
CFCong Fu
Cong Fu
YWYonglin Wu
Yonglin Wu
NSNing Shen
Ning Shen
Chen ChenChen Chen
Chen Chen
Deep learning methods have become an important tool for automatic sleep staging in recent years. However, most of the existing deep learning-based approaches are sharply constrained by the input modalities, where any insertion, substitution, and deletion of input modalities would directly lead to the unusable of the model or a deterioration in the performance. To solve the modality heterogeneity problems, a novel network architecture named MaskSleepNet is proposed. It consists of a masking module, a multi-scale convolutional neural network (MSCNN), a squeezing and excitation (SE) block, and a multi-headed attention (MHA) module. The masking module consists of a modality adaptation paradigm that can cooperate with modality discrepancy. The MSCNN extracts features from multiple scales and specially designs the size of the feature concatenation layer to prevent invalid or redundant features from zero-setting channels. The SE block further optimizes the weights of the features to optimize the network learning efficiency. The MHA module outputs the prediction results by learning the temporal information between the sleeping features. The performance of the proposed model was validated on two publicly available datasets, Sleep-EDF Expanded (Sleep-EDFX) and Montreal Archive of Sleep Studies (MASS), and a clinical dataset, Huashan Hospital Fudan University (HSFU). The proposed MaskSleepNet can achieve favorable performance with input modality discrepancy, e.g. for single-channel EEG signal, it can reach 83.8%, 83.4%, 80.5%, for two-channel EEG+EOG signals it can reach 85.0%, 84.9%, 81.9% and for three-channel EEG+EOG+EMG signals, it can reach 85.7%, 87.5%, 81.1% on Sleep-EDFX, MASS, and HSFU, respectively. In contrast the accuracy of the state-of-the-art approach which fluctuated widely between 69.0% and 89.4%. The experimental results exhibit that the proposed model can maintain superior performance and robustness in handling input modality discrepancy issues.

7 November 2022 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
WZWei Zhou
Wei Zhou
HYHaun Yu
Haun Yu
NSNing Shen
Ning Shen
HCHongyu Chen
Hongyu Chen
CFCong Fu
Cong Fu
Wei ChenWei Chen
Wei Chen
Sleep staging is the essential step in sleep quality assessment and sleep disorders diagnosis. However, most current automatic sleep staging approaches use recurrent neural networks (RNN), resulting in a relatively large training burden. Moreover, these methods only extract information of the whole epoch or adjacent epochs, ignoring the local signal variations within epoch. To address these issues, a novel deep learning architecture named segmented attention network (SAN) is proposed in this paper. The architecture can be divided into feature extraction (FE) and time sequence encoder (TSE). The FE module consists of multiple multiscale CNN (MMCNN) and residual squeeze and excitation block (SE block). The former extracts features from multiple equal-length EEG segments and the latter reinforced the features. The TSE module based on a multi-head attention mechanism could capture the temporal information in the features extracted by FE module. Noteworthy, in SAN, we replaced the RNN module with a TSE module for temporal learning and made the network faster. The evaluation of the model was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDFX, and one clinical dataset from Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed model achieved the accuracy of 85.5%, 86.4%, 82.5% on Sleep-EDFX, MASS and HSFU, respectively. The experimental results exhibited favorable performance and consistent improvements of SAN on different datasets in comparison with the state-of-the-art studies. It also proved the necessity of sleep staging by integrating the local characteristics within epochs and adjacent informative features among epochs.

2 August 2016 in PLOS ONE
Verified
Journal Article
Open access
PDF file
SHSi-Fei Huang
Si-Fei Huang
KCKui Chen
Kui Chen
JWJian-Jun Wu
Jian-Jun Wu
FLFeng-Tao Liu
Feng-Tao Liu
JZJue Zhao
Jue Zhao
Jian WangJian Wang
Jian Wang
Olfactory dysfunction is common in Parkinson's disease (PD) and idiopathic rapid eye movement sleep behavior disorder (iRBD), which is a risk factor in the development of PD. However, a few studies have conflicting results when comparing dysosmia in the patients with iRBD and PD. There is no study investigating the olfactory function in Chinese patients with iRBD. Additionally, the Sniffin’ Sticks screening 12 test (SS-12) contains several odors that are not familiar to people in different cultures. Odor identification was evaluated in iRBD patients (n = 54), PD patients (n = 54) and healthy controls (n = 54). With the identification data, a brief odor identification test was established and then validated in other subjects. Odor identification scores in iRBD patients were significantly higher than those in PD patients (P<0.001) but lower than those in controls (P<0.001). At the cut-off value of 7.5, the Sniffin’ Sticks clearly differentiated iRBD and PD patients from the controls, and the brief test could increase the specificity in diagnosing PD. Neither the Sniffin’ Sticks nor the brief test could clearly differentiate PD and iRBD patients from each other. Olfaction is more impaired in PD patients than in iRBD patients, possibly due to the heterogeneity of iRBD patients. The Sniffin’ Sticks could be a useful tool for differentiating iRBD patients from the healthy population, and it could be useful for screening people at high-risk of PD in China, especially when combined with polysomnography. To reduce the expense and time required for the Sniffin’ Sticks test, this study shows that a brief test is feasible.

10 May 2022 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
HYHaun Yu
Haun Yu
YWYonglin Wu
Yonglin Wu
NSNing Shen
Ning Shen
JFJiahao Fan
Jiahao Fan
LTLinkai Tao
Linkai Tao
Wei ChenWei Chen
Wei Chen
Elimination of intra-artifacts in EEG has been overlooked in most of the existing sleep staging systems, especially in deep learning-based approaches. Whether intra-artifacts, originated from the eye movement, chin muscle firing, or heart beating, etc., in EEG signals would lead to a positive or a negative masking effect on deep learning-based sleep staging systems was investigated in this paper. We systematically analyzed several traditional pre-processing methods involving fast Independent Component Analysis (FastICA), Information Maximization (Infomax), and Second-order Blind Source Separation (SOBI). On top of these methods, a SOBI-WT method based on the joint use of the SOBI and Wavelet Transform (WT) is proposed. It offered an effective solution for suppressing artifact components while retaining residual informative data. To provide a comprehensive comparative analysis, these pre-processing methods were applied to eliminate the intra-artifacts and the processed signals were fed to two ready-to-use deep learning models, namely two-step hierarchical neural network (THNN) and SimpleSleepNet for automatic sleep staging. The evaluation was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDF Expanded, and a clinical dataset that was collected in Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed SOBI-WT method increased the accuracy from 79.0% to 81.3% on MASS, 83.3% to 85.7% on Sleep-EDF Expanded, and 75.5% to 77.1% on HSFU compared with the raw EEG signal, respectively. Experimental results demonstrate that the intra-artifacts bring out a masking negative impact on the deep learning-based sleep staging systems and the proposed SOBI-WT method has the best performance in diminishing this negative impact compared with other artifact elimination methods.