Predictive value of stress hyperglycaemia ratio and haemoglobin glycation index for mortality risks in critically ill patients: a comparative retrospective analysis of the MIMIC-IV database using machine learning-based predictive modelling
Key Points
SHR and HGI associate strongly with mortality risks, indicating their predictive value.
The stress hyperglycaemia ratio is particularly effective for risk prevention in critically ill patients.
This analysis utilized machine learning-based predictive modelling for evaluating mortality risks.
The findings highlight the importance of using advanced modelling techniques for accurate mortality risk predictions.
Abstract
SHR and HGI showed a strong association with 360-day and short-term mortality risks. The SHR index appears to be the most promising index for prevention and risk stratification in critically ill patients.
Predictive value of stress hyperglycaemia ratio and haemoglobin glycation index for mortality risks in critically ill patients: a comparative retrospective analysis of the MIMIC-IV database using machine learning-based predictive modelling | Synapse