Association between the albumin-to-lymphocyte ratio and short-term mortality in critically Ill pediatric patients: a retrospective cohort study and machine learning analysis - Report - MDSpire
Advertisement
Association between the albumin-to-lymphocyte ratio and short-term mortality in critically Ill pediatric patients: a retrospective cohort study and machine learning analysis
Clinical Report: Link Between Albumin-to-Lymphocyte Ratio and Short-Term Mortality in Critically Ill Children
Overview
This study investigates the association between albumin-to-lymphocyte ratio (ALR) and short-term mortality in critically ill pediatric patients.
Background
Critically ill children often face rapid disease progression and high mortality rates due to various causes, including infections and trauma. Early risk stratification is crucial for optimizing resource allocation and improving outcomes in the PICU. The albumin-to-lymphocyte ratio (ALR) integrates nutritional and immune-inflammatory responses.
Data Highlights
ALR Tertile
28-Day Mortality Rate
Hazard Ratio (HR)
95% Confidence Interval (CI)
Lowest (T1)
Highest
-
-
Intermediate (T2)
Lowest
0.55
0.42-0.74
Highest (T3)
Lowest
0.65
0.49-0.86
Key Findings
The overall 28-day mortality rate among the studied cohort was 4.53%.
The intermediate ALR tertile (T2) showed the lowest observed 28-day mortality.
In the fully adjusted Cox model, both intermediate and highest tertiles were associated with lower mortality risk compared to the lowest tertile.
Restricted cubic spline analysis indicated a significant non-linear association between ALR and mortality.
The XGBoost machine learning model achieved an area under the curve (AUC) of 0.835 for predicting 28-day mortality.
Clinical Implications
ALR may be utilized as a simple and cost-effective biomarker for early risk assessment in critically ill pediatric patients. Its integration into clinical practice could enhance prognostic evaluations in the PICU.
Conclusion
ALR presents a promising tool for early risk stratification in critically ill children, potentially aiding in the identification of patients at higher risk of mortality.