Shufei Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shufei Zeng has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Bin Zhang
Department of Psychiatry, Nanfang Hospital, Southern Medical University, Guangzhou, China
3 shared publications - Leqin Fang
Department of Psychiatry, Sleep Medicine Center, Nanfang Hospital, Southern Medical University, Guangzhou, China
3 shared publications - Shixu Du
Department of Psychiatry, Sleep Medicine Center, Nanfang Hospital, Southern Medical University, Guangzhou, China
3 shared publications - Hangyi Yang
Department of Psychiatry, Sleep Medicine Center, Nanfang Hospital, Southern Medical University, Guangzhou, China
2 shared publications - Shuqiong Zheng
Department of Psychiatry, Sleep Medicine Center, Nanfang Hospital, Southern Medical University, Guangzhou, China
2 shared publications - Xue Luo
Department of Mental Health Education, Guangdong Mechanical & Electrical Polytechnic, Guangzhou 510515, China
2 shared publications
Latest Publications
- 3 July 2026
- Published by Zhejiang University Press in Journal of Zhejiang University-SCIENCE B
- Vol. 27 (9) , 1031-1040
Comparison of workplace impairment and daily activity impairment in acute and chronic insomnia disorder: a study of Chinese adults
- 3 July 2026
- Published by Zhejiang University Press in Journal of Zhejiang University-SCIENCE B
- Vol. 27 (9) , 1031-1040
Comparison of workplace impairment and daily activity impairment in acute and chronic insomnia disorder: a study of Chinese adults
- Open Access
- 1 January 2025
- Published by Wiley in Depression and Anxiety
- Vol. 2025 (1) , 8836588
Differential Anxiety–Depression–CRP Network Structures Across Insomnia Severity Levels: Evidence From UK Biobank
Background: This study investigated the relationships between anxiety, depression symptoms, and C‐reactive protein (CRP) across insomnia severity levels using network analysis and examined the structural differences within these networks. Methods: Gaussian graphical model network analysis with Least Absolute Shrinkage and Selection Operator (LASSO) regularization was conducted on UK Biobank data ( N = 143,027). Depression and anxiety symptoms were assessed using the 9‐item Patient Health Questionnaire (PHQ‐9) and 7‐item Generalized Anxiety Disorder Scale (GAD‐7), respectively. CRP was quantified using immunoturbidimetric‐high‐sensitivity analysis. Participants were categorized by insomnia frequency (never/rarely, sometimes, and usually). The strength symptoms and expected influence identified core symptoms, while bridge expected influence (bridge EI) determined bridge symptoms. Network comparison tests (NCTs) were performed pairwise across the three groups to assess differences in global strength and edge weights. Results: Across all networks, “Depressed mood” demonstrated the highest strength centrality, while “Irritability” exhibited the highest bridge EI. “Depressed mood” had the highest expected influence centrality in the never/rarely insomnia group and “Uncontrollable worry” in other groups. NCTs revealed significant differences in global strength ( S = 0.178, p < 0.01) and edge weights ( M = 0.062, p < 0.01) between the never/rarely and usually insomnia groups, with stronger connections between depressive symptoms (energy/appetite) and CRP in the usually insomnia group ( p < 0.001). Conclusions: The central roles of depressed mood, uncontrollable worry, and irritability in the anxiety–depression–CRP network across all insomnia severity groups suggest that these symptoms represent potential targets for future intervention research. Notably, network structure differed across insomnia severity; the strengthened associations between depressive symptoms and CRP in the usually insomnia group suggest that insomnia severity may be an important factor to consider in understanding the relationships between affective and inflammatory processes.
- 1 January 2025
- Published by Wiley in Depression and Anxiety
- Vol. 2025 (1) , 8836588
Open AccessDifferential Anxiety–Depression–CRP Network Structures Across Insomnia Severity Levels: Evidence From UK Biobank
Background: This study investigated the relationships between anxiety, depression symptoms, and C‐reactive protein (CRP) across insomnia severity levels using network analysis and examined the structural differences within these networks. Methods: Gaussian graphical model network analysis with Least Absolute Shrinkage and Selection Operator (LASSO) regularization was conducted on UK Biobank data ( N = 143,027). Depression and anxiety symptoms were assessed using the 9‐item Patient Health Questionnaire (PHQ‐9) and 7‐item Generalized Anxiety Disorder Scale (GAD‐7), respectively. CRP was quantified using immunoturbidimetric‐high‐sensitivity analysis. Participants were categorized by insomnia frequency (never/rarely, sometimes, and usually). The strength symptoms and expected influence identified core symptoms, while bridge expected influence (bridge EI) determined bridge symptoms. Network comparison tests (NCTs) were performed pairwise across the three groups to assess differences in global strength and edge weights. Results: Across all networks, “Depressed mood” demonstrated the highest strength centrality, while “Irritability” exhibited the highest bridge EI. “Depressed mood” had the highest expected influence centrality in the never/rarely insomnia group and “Uncontrollable worry” in other groups. NCTs revealed significant differences in global strength ( S = 0.178, p < 0.01) and edge weights ( M = 0.062, p < 0.01) between the never/rarely and usually insomnia groups, with stronger connections between depressive symptoms (energy/appetite) and CRP in the usually insomnia group ( p < 0.001). Conclusions: The central roles of depressed mood, uncontrollable worry, and irritability in the anxiety–depression–CRP network across all insomnia severity groups suggest that these symptoms represent potential targets for future intervention research. Notably, network structure differed across insomnia severity; the strengthened associations between depressive symptoms and CRP in the usually insomnia group suggest that insomnia severity may be an important factor to consider in understanding the relationships between affective and inflammatory processes.
- Open Access
- 1 January 2025
- Published by Wiley in Depression and Anxiety
- Vol. 2025 (1) , 3082856
Machine Learning Models to Identify Clinically Significant Anxiety in Short‐Term Insomnia Using Accelerometers
Clinically significant anxiety (CSA) is common in individuals with short‐term insomnia. This study aims to explore the relationship between CSA and the subjective and objective parameters of sleep in patients with short‐term insomnia and construct machine learning (ML) models to determine the utility of accelerometer features in identifying significant anxiety. A total of 205 short‐term insomnia participants from China were assigned to the group with CSA ( N = 33) or the group without CSA ( N = 172). Interaction analysis based on linear regression was used to estimate the possible interactive effect of accelerometer features between CSA and sleep problems. Four feature sets and eight algorithms were used to construct ML models, with Shapley Additive exPlanations (SHAP) values used to visualize feature importance and influence processes. CSA in patients with short‐term insomnia leads to more severe subjective sleep problems, and accelerometer‐measured features warrant further attention for the identification of interactive factors. A significant interaction effect was found between anxiety symptoms and longer duration of physical activity on insomnia severity ( P interaction < 0.05). Anxiety symptoms and interdaily stability had an interactive association with sleep hygiene behaviors ( P interaction < 0.01). ML can process and analyze complex accelerometer features to identify CSA in patients with short‐term insomnia. Compared with other feature sets and algorithms, the XGBoost model with accelerometer‐measured features on weekdays more effectively identified CSA with area under the curve (AUC) value of 0.777. SHAP analysis results indicated that circadian rhythm features had significant contributions. Decision plots based on SHAP were applied to visualize the personalized risk factors for each patient and provide clinicians with more easily understandable and practical explanation methods that enhance clinical decision‐making. Trial Registration: Chinese Clinical Trial Registry identifier: ChiCTR2200062910
- 1 January 2025
- Published by Wiley in Depression and Anxiety
- Vol. 2025 (1) , 3082856
Open AccessMachine Learning Models to Identify Clinically Significant Anxiety in Short‐Term Insomnia Using Accelerometers
Clinically significant anxiety (CSA) is common in individuals with short‐term insomnia. This study aims to explore the relationship between CSA and the subjective and objective parameters of sleep in patients with short‐term insomnia and construct machine learning (ML) models to determine the utility of accelerometer features in identifying significant anxiety. A total of 205 short‐term insomnia participants from China were assigned to the group with CSA ( N = 33) or the group without CSA ( N = 172). Interaction analysis based on linear regression was used to estimate the possible interactive effect of accelerometer features between CSA and sleep problems. Four feature sets and eight algorithms were used to construct ML models, with Shapley Additive exPlanations (SHAP) values used to visualize feature importance and influence processes. CSA in patients with short‐term insomnia leads to more severe subjective sleep problems, and accelerometer‐measured features warrant further attention for the identification of interactive factors. A significant interaction effect was found between anxiety symptoms and longer duration of physical activity on insomnia severity ( P interaction < 0.05). Anxiety symptoms and interdaily stability had an interactive association with sleep hygiene behaviors ( P interaction < 0.01). ML can process and analyze complex accelerometer features to identify CSA in patients with short‐term insomnia. Compared with other feature sets and algorithms, the XGBoost model with accelerometer‐measured features on weekdays more effectively identified CSA with area under the curve (AUC) value of 0.777. SHAP analysis results indicated that circadian rhythm features had significant contributions. Decision plots based on SHAP were applied to visualize the personalized risk factors for each patient and provide clinicians with more easily understandable and practical explanation methods that enhance clinical decision‐making. Trial Registration: Chinese Clinical Trial Registry identifier: ChiCTR2200062910