ORIGINAL RESEARCH article
Front. Nutr.
Sec. Nutrition and Metabolism
Volume 12 - 2025 | doi: 10.3389/fnut.2025.1649553
Correlation of triglyceride-glucose index with the incidence and prognosis of hyperglycemic crises in critically ill patients with diabetes mellitus: a machine-learning-based multicenter retrospective cohort study
Provisionally accepted
- The Affiliated Hospital of Qingdao University, Qingdao, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Background: Hyperglycemic crisis events (HCEs) — encompassing diabetic ketoacidosis (DKA) and hyperosmolar hyperglycemic state (HHS)—constitute lethal determinants for patients with diabetic mellitus (DM) in intensive care. The triglyceride-glucose (TyG) index, an emergent insulin resistance surrogate, lacks rigorous investigation regarding HCE occurrence trajectories and prognostic sequelae among critically ill diabetics.This study aims to evaluate the relationship between the TyG index and HCE incidence/clinical outcomes in critically ill DM patients and to construct a risk prediction model using machine learning algorithms. Methods: This multi-center retrospective investigation leveraged clinical repositories from Medical Information Mart for Intensive Care IV (MIMIC-IV) and eICU Collaborative Research Database (eICU-CRD). Inclusion criteria encompassed critically ill diabetic subjects possessing computable TyG indices within 24 hours post-admission. The main study endpoints included death occurring during hospitalization and death within the intensive care unit. TyG index-outcome interrelationships underwent interrogation via logistic regression, restricted cubic spline (RCS), correlation, and linear analytical methodologies. Overlap weighting (OW), inverse probability treatment weighting (IPTW), and propensity score matching (PSM) mitigated confounding influences. Stratified examinations occurred per determinant factors. Five machine learning architectures constructed mortality prognostication frameworks, with Shapley Additive Explanations (SHAP) delineating pivotal predictors. Results: Among 4,098 critically ill DM patients, 328 developed HCE. HCE patients had significantly higher TyG levels [10.2 (9.6–11.0) vs. 9.4 (8.9–9.9)] than non-HCE patients, demonstrating TyG's discriminative ability for HCE. Through multivariate logistic regression, TyG was pinpointed as a separate risk element for both in-hospital (OR 1.956) and ICU death (OR 2.260), linked to extended hospital stays. RCS established a direct positive correlation between increased TyG levels and death rates (nonlinear P = 0.161 and 0.457), continuing even after adjusting for PSM, OW, and IPTW. Subgroup analyses reinforced TyG's consistent mortality correlation. Machine learning models, particularly XGBoost, achieved higher predictive accuracy, with TyG as a key component. Conclusion: Elevated TyG index shows a notable correlation with the occurrence of HCE and negative results in patients with critically ill DM. Advanced multivariate machine learning models are adept at pinpointing patients at high risk, thereby facilitating prompt clinical action.
Keywords: Triglyceride-glucose index, Hyperglycemic crisis, Critical Care, machine learning, Mortality prediction
Received: 18 Jun 2025; Accepted: 20 Aug 2025.
Copyright: © 2025 Xie, Zhang, Wu, Wu, Han, Xie, Zhang, Cheng and Xu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Rui Zhang, The Affiliated Hospital of Qingdao University, Qingdao, China
Jianhua Cheng, The Affiliated Hospital of Qingdao University, Qingdao, China
Jian Xu, The Affiliated Hospital of Qingdao University, Qingdao, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.