Related Experiment Video
Updated: Apr 8, 2026
An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Development and validation of a prognostic model and scoring system for in-hospital mortality risk in neonates with
Meng Wei1,2, Xinru Liu3, Gaofeng Sun4
1Department of Cardiac Pacing and Electrophysiology, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, 830000, Xinjiang, China.
Insights
A new scoring system helps predict death risk in neonatal heart failure patients. It identifies high-risk infants early, guiding personalized treatment to improve outcomes for this severe condition.
Area of Science:
- Pediatrics
- Cardiology
- Neonatology
Background:
- Neonatal heart failure (NHF) presents a significant mortality risk.
- Early prediction of mortality is vital for timely intervention and improved outcomes in NHF.
- Existing predictive tools for NHF mortality are limited.
Purpose of the Study:
- To develop and validate a predictive model and scoring system for 28-day in-hospital mortality in neonates with heart failure.
- To identify key clinical and laboratory factors associated with mortality in this population.
Main Methods:
- A multicenter retrospective study involving 579 neonates (training/internal validation) and 118 (external validation).
- Lasso regression for variable selection, followed by logistic regression to build the predictive model.
- Development of a scoring system to stratify mortality risk into low, medium, and high categories.
Main Results:
- Lasso identified 20 key variables. Factors increasing mortality risk included low fibrinogen (<2 g/L), poor postnatal response, and oliguria.
- Medications like digoxin, cedilanid, dopamine, and epinephrine were associated with reduced mortality risk.
- The predictive model demonstrated strong performance with AUCs of 0.87 (training), 0.83 (internal validation), and 0.85 (external validation).
Conclusions:
- A validated predictive model and scoring system for neonatal heart failure mortality have been established.
- This tool enables early identification of high-risk neonates, facilitating individualized treatment strategies.
- The findings can guide clinical decision-making and potentially improve survival rates in neonatal heart failure.
Abstract:
Neonatal heart failure is a severe condition with high mortality, posing a significant burden on families and healthcare systems. Early prediction of mortality risk is crucial for improving outcomes. To develop and validate a predictive model and scoring system for in-hospital mortality within 28 days in neonates with heart failure. This multicenter retrospective study included 579 neonates from the First Affiliated Hospital of Xinjiang Medical University (training and internal validation sets) and 118 from Beijing Anzhen Hospital (external validation set). Data included sociodemographic characteristics, clinical symptoms, medical history, medication use, laboratory results, and outcomes. Lasso was used for variable selection from a large set of candidates, followed by logistic regression on the selected variables to build the final model and scoring system. Lasso regression identified 20 key variables. This study found that fibrinogen < 2 g/L, poor postnatal response, and oliguria were associated with an increased risk of death in neonates with heart failure, while the use of digoxin, cedilanid, dopamine, and epinephrine reduced the risk of death. The model showed AUC values of 0.87 (95% CI: 0.82-0.91), 0.83 (95% CI: 0.77-0.90), and 0.85 (95% CI: 0.77-0.93) in the training, internal validation, and external validation sets, respectively. The scoring system effectively categorized patients into low, medium, and high-risk groups. This study established a predictive model and scoring system for in-hospital mortality risk in neonates with heart failure, enabling early identification of high-risk infants and guiding individualized treatment strategies to improve outcomes.
