Risk prediction models for cardiovascular events in hemodialysis patients: A systematic review

Tiantian Gan^1* Hua Guan² Pengli Li² Xingping Huang¹ Yue Li²

• ¹College of Nursing, Chengdu University of Traditional Chinese Medicine, China
• ²Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, China

The purpose of this study was to conduct a systematic evaluation of risk prediction models for cardiovascular events (CVE) in patients undergoing hemodialysis (HD), providing a reference basis for the application and optimization of related prediction models.Methods: PubMed, The Cochrane Library, Web of Science, and Embase databases were searched from inception to July 1, 2023. After independent screening and data extraction by two researchers, the Prediction Model Risk of Bias Assessment Tool (PROBAST) was applied to evaluate the risk of bias and applicability of the included studies.Results: A total of 11 studies containing 15prediction models were included, with performance measured by the area under the receiver operating characteristic curve (AUC) lying between 0.70 to 0.88. Age, history of diabetes, CRP, and ALB were the most commonly identified predictors of CVE in HD patients. While the included models demonstrated good applicability, there were still certain risks of bias, primarily related to inadequate handling of missing data and transformation of continuous variables, as well as a lack of model performance validation.The included models exhibited good predictive performance and can assist clinical practitioners in the early identification of high-risk individuals for CVE in HD patients. In the future, the modeling methods should be improved, or the existing models should undergo external validation to provide better guidance for clinical practice.