Yulu Zheng

Yulu Zheng

Auto-generated profile, based on publicly available information

Yulu Zheng

Centre for Precision Health Edith Cowan University Joondalup Australia

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
27 May 2022 in EPMA Journal
Verified
Journal Article
Open access
PDF file
YZYulu Zheng
Yulu Zheng
ZGZheng Guo
Zheng Guo
YZYanbo Zhang
Yanbo Zhang
JSJianjing Shang
Jianjing Shang
LYLeilei Yu
Leilei Yu
O(on behalf of Global Health Epidemiology Reference Group (GHERG)
on behalf of Global Health Epidemiology Reference Group (GHERG)
Background: Recognising the early signs of ischemic stroke (IS) in emergency settings has been challenging. Machine learning (ML), a robust tool for predictive, preventive and personalised medicine (PPPM/3PM), presents a possible solution for this issue and produces accurate predictions for real-time data processing. Methods: This investigation evaluated 4999 IS patients among a total of 10,476 adults included in the initial dataset, and 1076 IS subjects among 3935 participants in the external validation dataset. Six ML-based models for the prediction of IS were trained on the initial dataset of 10,476 participants (split participants into a training set [80%] and an internal validation set [20%]). Selected clinical laboratory features routinely assessed at admission were used to inform the models. Model performance was mainly evaluated by the area under the receiver operating characteristic (AUC) curve. Additional techniques—permutation feature importance (PFI), local interpretable model-agnostic explanations (LIME), and SHapley Additive exPlanations (SHAP)—were applied for explaining the black-box ML models. Results: Fifteen routine haematological and biochemical features were selected to establish ML-based models for the prediction of IS. The XGBoost-based model achieved the highest predictive performance, reaching AUCs of 0.91 (0.90–0.92) and 0.92 (0.91–0.93) in the internal and external datasets respectively. PFI globally revealed that demographic feature age, routine haematological parameters, haemoglobin and neutrophil count, and biochemical analytes total protein and high-density lipoprotein cholesterol were more influential on the model’s prediction. LIME and SHAP showed similar local feature attribution explanations. Conclusion: In the context of PPPM/3PM, we used the selected predictors obtained from the results of common blood tests to develop and validate ML-based models for the diagnosis of IS. The XGBoost-based model offers the most accurate prediction. By incorporating the individualised patient profile, this prediction tool is simple and quick to administer. This is promising to support subjective decision making in resource-limited settings or primary care, thereby shortening the time window for the treatment, and improving outcomes after IS.

1 October 2022 in Journal of Global Health
Verified
Journal Article
Open access
ZGZheng Guo
Zheng Guo
RMRuoyu Meng
Ruoyu Meng
YZYulu Zheng
Yulu Zheng
XLXingang Li
Xingang Li
ZZZiqi Zhou
Ziqi Zhou
S(Suboptimal Health Study Consortium (SHSC) and the Global Health Epidemiology Research Group (GHERG)
Suboptimal Health Study Consortium (SHSC) and the Global Health Epidemiology Research Group (GHERG)
The World Health Organization (WHO) defines health as “a state of complete physical, mental and social well-being and not merely the absence of disease or infirmity” [1]. With the rapidly increasing pace of life and daily stress which characterize modern society, the number of people experiencing adverse chief complaints is on the rise [2]. These […]

6 September 2022 in Journal of Global Health
Verified
Journal Article
Open access
ZGZheng Guo
Zheng Guo
JWJun Wen
Jun Wen
DZDanni Zheng
Danni Zheng
ZYZheng Yulu
Zheng Yulu
HHHaifeng Hou
Haifeng Hou
S(Suboptimal Health Study Consortium (SHSC)
Suboptimal Health Study Consortium (SHSC)
The COVID-19 outbreak has posed tremendous threats to both global health and individuals’ psychological and physiological well-being. Scholars across the social and medical sciences are calling for multidisciplinary research regarding how the COVID-19 pandemic has affected global health [1]. As daily stressors continue to accumulate, the number of people reporting health complaints that cannot be […]

21 September 2025 in Health Science Reports
Verified
Journal Article
Open access
ZGZheng Guo
Zheng Guo
YZYulu Zheng
Yulu Zheng
YZYahong Zhu
Yahong Zhu
HWHuacheng Wang
Huacheng Wang
JGJian Geng
Jian Geng
XLXingang Li
Xingang Li
Background and Aims: Social isolation has been linked to depressive symptoms in older adults. Previous studies have shown that greater engagement in social activities is associated with better mental health. However, it remains unclear whether restricted social engagement is related to poorer mental health outcomes. This study examined the association between reduced social activities/networking and the presence of depressive symptoms among community‐dwelling older Chinese adults. Methods: During the COVID‐19 pandemic, people chose to minimize going out to reduce the risk of infection, creating a natural setting that mimicked a passive intervention of restricted social engagement for community‐based individuals. Data were drawn from 7288 participants aged ≥ 65 years from the fifth wave (2019–2020) wave of the China Health and Retirement Longitudinal Study. Depressive symptoms were measured using the 10‐item Center for Epidemiologic Studies Depression Scale. Social activities/networking changes due to COVID‐19 were self‐reported. Multivariable logistic regression examined associations between activity changes and depressive symptoms, adjusting for demographics and anxiety/fear levels. Results: Among 7288 participants (49.8% female;mean age 73.1, SD = 6.6), 41.4% exhibited depressive symptoms. The prevalence of depressive symptoms was higher among females (50.3%) than males (32.7%). Higher education levels were associated with a lower prevalence of depressive symptoms. Participants reporting anxiety or fear were more likely to exhibit depressive symptoms. After adjusting for potential confounders, including social demographics and other mental problems, multivariate logistic regression analysis revealed reduced contact with other people was a significant risk factor for depression, whereas reduced participation in social gatherings was unexpectedly associated with a lower risk of depressive symptoms. Conclusions: Reduced social engagement and related health behaviors were associated with an increased likelihood of depressive symptoms among Chinese older adults during the COVID‐19 pandemic. Interventions that promote social participation and healthy lifestyles may help protect mental health in this vulnerable population.

31 July 2024 in EPMA Journal
Verified
Journal Article
Open access
PDF file
MGMonique Garcia
Monique Garcia
ZGZheng Guo
Zheng Guo
YZYulu Zheng
Yulu Zheng
ZWZhiyuan Wu
Zhiyuan Wu
EVEthan Visser
Ethan Visser
Wei WangWei Wang
Wei Wang
Background: Suboptimal Health Status (SHS) is the physical state between health and disease. This study aimed to fill in the knowledge gap by investigating the prevalence of SHS and psychological symptoms among unpaid carers and to identify SHS-risk factors from the perspective of predictive, preventive and personalised medicine (PPPM). Methods: A cross-sectional study was conducted among 368 participants who were enrolled from Australia, including 203 unpaid carers as cases and 165 individuals from the general population as controls. SHS scores were measured using SHSQ-25 (Suboptimal Health Status Questionnaire-25), whilst psychological symptoms were measured by DASS-21 (Depression, Anxiety and Stress Scale-21). Chi-square was used to measure SHS and psychological symptom prevalence. Spearman correlation analysis was utilised to identify the relationship between SHSQ-25 and DASS-21 scores. Logistic regression analysis was used for multivariate analysis. Results: The prevalence of SHS in carers was 43.0% (98/203), significantly higher than the prevalence 12.7% (21/165) in the general population (p < 0.001). In addition, suboptimal health prevalence was higher in female carers (50.3%; 95/189) than females in the general population (12.4%; 18/145). Logistic regression showed that the caregiving role influenced SHS, with carers 6.4 times more likely to suffer from SHS than their non-caring counterparts (aOR = 6.400, 95% CI = 3.751–10.919). Conclusions: Unpaid carers in Australia have a significantly higher prevalence of SHS than that in the general population and experience poorer health. The SHSQ-25 is a powerful tool that can be utilised to screen at-risk individuals to predict their risk of chronic disease development, an essential pillar for shifting the paradigm change from reactive medicine to that of predictive, preventive and personalised medicine (PPPM).

22 July 2025 in Annals of Internal Medicine
Verified
Journal Article
Closed access
ZWZhiyuan Wu
Zhiyuan Wu
CSChen Sheng
Chen Sheng
ZGZheng Guo
Zheng Guo
YZYulu Zheng
Yulu Zheng
DZDeqiang Zheng
Deqiang Zheng
HLHaibin Li
Haibin Li
"Weekend warrior" and regularly active physical activity patterns have been associated with reduced mortality risk in the general population. The association in patients with diabetes is unknown. To examine the associations of different physical activity patterns, particularly weekend warrior and regularly active behavior, with all-cause, cardiovascular, and cancer mortality among adults with diabetes. Prospective cohort study. National Health Interview Survey (1997 to 2018) linked to the National Death Index records through 31 December 2019. 51 650 U.S. adults with self-reported diabetes. Participants categorized by 4 physical activity groups: inactive (reporting no moderate-to-vigorous physical activity [MVPA]), insufficiently active (MVPA <150 minutes per week), weekend warrior (MVPA ≥150 minutes per week in 1 to 2 sessions), and regularly active (MVPA ≥150 minutes per week in ≥3 sessions). During a median follow-up of 9.5 years, 16 345 deaths (cardiovascular, 5620; cancer, 2883) were documented. Compared with inactive participants, multivariable-adjusted hazard ratios (HRs) for all-cause mortality were significantly lower across physical activity groups: insufficiently active persons (HR, 0.90 [95% CI, 0.85 to 0.95]), weekend warriors (HR, 0.79 [CI, 0.69 to 0.91]), and regularly active persons (HR, 0.83 [CI, 0.78 to 0.87]). These reductions were mostly due to benefits with cardiovascular mortality: insufficiently active persons (HR, 0.98 [CI, 0.89 to 1.07]), weekend warriors (HR, 0.67 [CI, 0.52 to 0.86]), and regularly active persons (HR, 0.81 [CI, 0.74 to 0.88]). There were fewer differences by cancer mortality: insufficiently active persons (HR, 0.88 [CI, 0.78 to 1.00]), weekend warriors (HR, 0.99 [CI, 0.76 to 1.30]), and regularly active persons (HR, 0.85 [CI, 0.75 to 0.96]). Physical activity was self-reported and assessed at a single time point. Weekend warrior and regularly active physical activity patterns meeting current physical activity recommendations (MVPA ≥150 minutes per week) were associated with 21% and 17% lower risks for all-cause mortality and 33% and 19% lower hazards of cardiovascular mortality among adults with diabetes compared with those with diabetes who are physically inactive. Capital's Funds for Health Improvement and Research, and National Natural Science Foundation of China.