Combined assessment of stress hyperglycemia ratio and glycemic variability to predict all-cause mortality in critically ill patients with atherosclerotic cardiovascular diseases across different glucose metabolic states: an observational cohort study with machine learning
Authors' conclusion
Combined SHR and GV assessment serves as a critical prognostic tool for ASCVD mortality, providing enhanced predictive accuracy compared to individual metrics, particularly in NGR and Pre-DM patients. This integrated approach could inform personalized glycemic management strategies, potentially improving clinical outcomes.
Study context
- Population
- Critically ill patients with atherosclerotic cardiovascular disease (ASCVD) in Medical Information Mart for Intensive Care IV (MIMIC-IV), stratified into normal glucose regulation (NGR), pre-diabetes mellitus (Pre-DM) and diabetes mellitus (DM); median age 71 years, 58.78% male
- Participants
- 2,807 patients
- Exposure
- Combined SHR-GV assessment vs stress hyperglycemia ratio (SHR) alone and glycemic variability (GV) alone for mortality prediction
- Outcome
- 28-day mortality
- Follow-up
- 28 days
Methodological detailsobservational, MIMIC-IV database, machine learning
- Observational
- MIMIC-IV database
- Machine learning
Main finding
As reported in the abstract
Prediction of 28-day mortality (AUC), by glucose metabolic state
- SHR-GV vs SHR · NGR
- AUC 0.688 (0.636-0.739) vs. 0.623 (0.568-0.679); P = 0.028
- SHR-GV vs SHR · Pre-DM
- AUC 0.712 (0.659-0.764) vs. 0.639 (0.582-0.696); P = 0.102
- SHR-GV vs GV · NGR
- AUC 0.688 vs. 0.578 (0.524-0.633); P < 0.001
- SHR-GV vs GV · Pre-DM
- AUC 0.712 vs. 0.593 (0.524-0.652); P < 0.001
- Overall 28-day mortality
- 483 (23.14%)
Observational data: associations, not effects.
Secondary outcomes
| Outcome | AUC | P value |
|---|---|---|
| Prediction of 90-day mortality · 90 daysSHR-GV vs SHR · DM | 0.578 (0.541-0.616) vs. 0.560 (0.520-0.599) | P = 0.027 |
- Prediction of 90-day mortality — Overall 90-day mortality
- 608 (29.13%)
Prediction of 90-day mortality
- Consistent findings for 90-day mortality prediction in NGR and Pre-DM
- DM: no significant advantages in other comparisons
Original publication
Combined assessment of stress hyperglycemia ratio and glycemic variability to predict all-cause mortality in critically ill patients with atherosclerotic cardiovascular diseases across different glucose metabolic states: an observational cohort study with machine learning. Cardiovasc Diabetol. Published 9 May 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →