Joint effect of triglyceride-glucose index and low-density lipoprotein cholesterol on mortality and days alive out of hospital in acute stroke: a multi-center machine learning-based cohort study
Main finding · Highest in-hospital mortalityResult — go to the resultOdds ratio 3.36 95% CI 2.37–4.76Authors' conclusion
High TyG combined with low LDL-C identifies a high-risk phenotype in acute stroke, significantly associated with adverse outcomes.
Study context
- Population
- Patients with acute stroke in MIMIC (derivation) and eICU-CRD (external validation) databases3,028 MIMIC + 2,385 eICU
- Exposure
- Combined triglyceride-glucose (TyG) index and LDL-C categories
- Outcome
- Mortality and days alive out of hospital (DAOH90)
Methodological detailsmulti-center, derivation cohort (MIMIC) with external validation (eICU-CRD), machine learning-based
- Multi-center
- Derivation cohort (MIMIC) with external validation (eICU-CRD)
- Machine learning-based
Main finding
Highest in-hospital mortality
Odds ratio
3.36
95% CI 2.37–4.76
Low LDL-C + high TyG
OR 3.36 (95% CI 2.37–4.76)
As reported in the abstract
Observational data: associations, not effects.
Further findings
Inpatient statin use
- Inpatient statin use was associated with lower mortality
Mediation by WBC of TyG–in-hospital mortality association
- Proportion mediated by WBC
- 15.46%
Machine-learning prediction of mortality (nine selected predictors)
- GBM best performance, AUC
- 0.802
Original publication
Joint effect of triglyceride-glucose index and low-density lipoprotein cholesterol on mortality and days alive out of hospital in acute stroke: a multi-center machine learning-based cohort study. Diabetes Res Clin Pract. Published 24 September 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →