Meng Yuan

Meng Yuan

Auto-generated profile, based on publicly available information

Meng Yuan

Department of Intensive Care Unit, Huzhou Central Hospital, Affiliated Central Hospital of Huzhou University, Zhejiang, China; Department of Anesthesiology, Huzhou Central Hospital, Affiliated Central Hospital of Huzhou University, Zhejiang, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
8 March 2024 in Heliyon
Verified
Journal Article
Open access
XGXiaoyue Guan
Xiaoyue Guan
LZLei Zhong
Lei Zhong
JZJinyu Zhang
Jinyu Zhang
JLJianhong Lu
Jianhong Lu
MYMeng Yuan
Meng Yuan
JMJie Min
Jie Min
Sepsis is a prevalent and severe medical condition which is frequently observed in the intensive care unit (ICU). Although numerous biomarkers have been identified to predict the prognosis of sepsis, the lactate dehydrogenase to albumin ratio (LDH/ALB ratio) has not been extensively investigated. The principal objective of this study is to assess the relationship between LDH/ALB ratio and all-cause mortality in patients with sepsis. This study included all adult critically ill patients with sepsis from the Medical Information Mart for Intensive Care IV (MIMIC-IV, version 2.0) database. Propensity score matching (PSM) analysis was conducted to mitigate bias, and Kaplan-Meier curves were performed to evaluate the cumulative survival across different groups. The association between the LDH/ALB ratio and mortality was examined through restricted cubic spline (RCS) analysis and Cox regression analysis. The robustness of the findings was confirmed through subgroup analyses. Additionally, the prognostic capability of the LDH/ALB ratio was further evaluated using receiver operating characteristic (ROC) curve analysis. There were 6059 adult patients with sepsis enrolled in the final analysis. RCS revealed a non-linear relationship between the LDH/ALB ratio and an increased risk of ICU all-cause mortality (χ2 = 46.900, P < 0.001). Following PSM analysis, 1553 matched pairs were obtained. As comparison to the low LDH/ALB ratio group, the mortality rate in the high LDH/ALB ratio group was significantly higher (P < 0.001). Kaplan-Meier curves, both before and after PSM, revealed that the ICU cumulative survival rate for patients with sepsis was significantly lower in the high LDH/ALB ratio group compared to the low LDH/ALB ratio group (χ2 = 93.360, P < 0.001; χ2 = 14.400, P < 0.001). Even after adjusting for a range of potential confounders, multivariate Cox regression analysis indicated that an elevated LDH/ALB ratio was a significant predictor of all-cause mortality in these patients. ROC curve analysis demonstrated that the LDH/ALB ratio had an area under the ROC curve (AUC) of 0.688 for predicting ICU mortality, with a sensitivity of 69.2% and a specificity of 58.6%. An elevated LDH/ALB ratio (≥10.57) was associated with all-cause mortality in critically ill patients with sepsis, and it might serve as a prognostic marker. Clinicians should pay closer attention to sepsis patients presenting with an LDH/ALB ratio of 10.57 or higher.

8 September 2026 in Clinics
Verified
Journal Article
Open access
MYMeng Yuan
Meng Yuan
LZLei Zhong
Lei Zhong
JMJie Min
Jie Min
MNMingxia Ni
Mingxia Ni
YYYufeng Yao
Yufeng Yao
Cardiac Arrest (CA) often leads to Acute Kidney Injury (AKI), presenting a major health issue. This study aims to develop and validate machine learning models predicting 30-day mortality in CA patients with AKI. A retrospective study was conducted on 1,121 adult ICU patients diagnosed with CA and AKI using data from the MIMIC-IV database. Data from 2008‒2016 (n = 900) formed the training cohort, while 2017‒2019 data (n = 221) served as the temporal validation cohort. Feature selection utilized LASSO regression, followed by the application of six machine learning algorithms. Model performance was evaluated using ROC curves, calibration curves, and decision curve analysis, with comparisons made against the APACHE II and SOFA scores. Seven key features were identified, namely, APACHE II score, lactate, anion gap, RDW, oliguria, norepinephrine, and temporary pacemaker implantation. The LASSO-Logistic Regression (LASSO-LR) model demonstrated the most stable performance in validation (AUROC = 0.751), significantly outperforming APACHE II (0.583, p < 0.001) and SOFA (0.660, p = 0.009), with a Brier score of 0.209. SHAP analysis revealed oliguria and RDW as the most significant predictors. The LASSO-LR model offers a modest but statistically significant improvement over conventional scoring systems for predicting 30-day mortality in patients with CA and AKI, with acceptable calibration and interpretability. However, the clinical meaningfulness of this incremental benefit requires prospective validation before clinical implementation.