Related Experiment Video
Updated: Jul 1, 2026
Clinical Application of Phase Angle and BIVA Z-Score Analyses in Patients Admitted to an Emergency Department with Acute Heart Failure
Published on: June 30, 2023
Predicting short-term composite outcome risk in heart failure patients using a machine learning model incorporating
Yihe Zhang1, Xu Zhang2, Hongbin Song3
1Department of Clinical Laboratory, Beijing Anzhen Hospital, Capital Medical University, Beijing, China.
Insights
The uric acid-to-high-density lipoprotein cholesterol ratio (UHR) is an independent risk factor for heart failure (HF) prognosis. An XGBoost model incorporating UHR and other clinical indicators accurately predicts HF outcomes.
Area of Science:
- Cardiology
- Biomarker Research
- Machine Learning in Healthcare
Background:
- The uric acid-to-high-density lipoprotein cholesterol ratio (UHR) is a composite biomarker indicating oxidative stress and antioxidant imbalance.
- Previous studies suggest UHR is linked to poor heart failure (HF) prognosis, but require independent validation and integration into risk prediction tools.
Purpose of the Study:
- To independently validate the association between UHR and a 180-day composite outcome (all-cause death or HF rehospitalization) in a large HF cohort.
- To develop an interpretable machine learning model incorporating UHR and routine clinical indicators for individualized risk prediction.
Main Methods:
- A retrospective cohort study of 2,737 HF patients with 180-day follow-up.
- Analysis included multivariate Cox regression, restricted cubic splines (RCS), and LASSO regression for variable selection.
- Seven machine learning models were developed and validated internally; the optimal model was interpreted using SHAP and deployed as an online calculator.
Main Results:
- A composite outcome occurred in 33.8% of patients during follow-up.
- UHR was confirmed as an independent risk factor with a nonlinear association with the composite outcome.
- The eXtreme Gradient Boosting (XGBoost) model, using UHR, BMI, hyperlipidemia history, Hcy, GA, and sdLDL-C, achieved an AUC of 0.866 in validation.
Conclusions:
- UHR is a significant independent risk factor for short-term adverse outcomes in HF patients.
- The developed XGBoost model demonstrates strong predictive performance for HF risk stratification.
- The online calculator serves as a research tool, requiring external validation before clinical application.
Introduction:
The uric acid-to-high-density lipoprotein cholesterol ratio (UHR) is a composite biomarker that reflects both oxidative stress and antioxidant imbalance. Previous studies have linked UHR to poor prognosis in heart failure (HF), but the evidence relies largely on traditional regression models; it lacks independent validation and has not been integrated into modern, individualized risk-prediction tools. This study aimed to independently validate the association between UHR and a 180-day composite outcome (all-cause death or HF rehospitalization) in a relatively large HF cohort, and to construct an interpretable machine learning model that incorporates UHR and routine clinical indicators.
Methods:
This was a single-center retrospective cohort study that consecutively enrolled 2,737 patients with heart failure hospitalized at Beijing Anzhen Hospital, Capital Medical University, from January 1, 2024, to June 30, 2025. All patients were followed up until December 31, 2025, to ensure complete 180-day follow-up data for each patient. The primary outcome was a composite endpoint of all-cause death or heart failure rehospitalization within 180 days. Multivariate Cox regression and restricted cubic splines (RCS) were used to analyze the association and dose-response relationship between UHR and the composite outcome. Least Absolute Shrinkage and Selection Operator (LASSO) regression combined with multivariate Logistic regression was employed to screen predictive variables. Seven machine learning models were developed in the training set (n = 1,917) and validated in an internal validation set (n = 820). The optimal model was interpreted using the SHapley Additive exPlanations (SHAP) framework and deployed as an online calculator.
Results:
During follow-up, 926 patients (33.8%) experienced the composite outcome. UHR was confirmed as an independent risk factor for the composite outcome. RCS analysis revealed a nonlinear association. The eXtreme Gradient Boosting (XGBoost) model, constructed based on six variables: body mass index (BMI), history of hyperlipidemia, homocysteine (Hcy), glycated albumin (GA), small dense low-density lipoprotein cholesterol (sdLDL-C) and UHR, demonstrated the best performance. In the internal validation set, it achieved an AUC of 0.866 (95%CI, 0.839-0.890), with good calibration and high clinical net benefit in decision curve analysis. SHAP analysis identified sdLDL-C and UHR as the two most important predictive features and revealed nonlinear effects of the variables. The model was deployed as an online calculator (https://machine11.shinyapps.io/xgboostforUHR/), which currently serves as a research demonstration platform and requires external validation before any clinical application.
Discussion:
UHR is an independent risk factor for the 180-day composite outcome in HF patients. The XGBoost model based on UHR and five other routine clinical indicators shows good discrimination, calibration, and clinical net benefit. The online calculator provides an exploratory tool for short-term risk stratification but requires further external validation before clinical use.