Table 1_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.docx

Background<p>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 su...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Mingchen Xie (4325692) (author)
مؤلفون آخرون: Yahui Zhang (444739) (author), Haitao Wu (2411155) (author), Zeyu Wu (455882) (author), Hao Han (412732) (author), Xun Xie (15557433) (author), Rui Zhang (13940) (author), Jianhua Cheng (467464) (author), Jian Xu (31545) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852016991924125696
author Mingchen Xie (4325692)
author2 Yahui Zhang (444739)
Haitao Wu (2411155)
Zeyu Wu (455882)
Hao Han (412732)
Xun Xie (15557433)
Rui Zhang (13940)
Jianhua Cheng (467464)
Jian Xu (31545)
author2_role author
author
author
author
author
author
author
author
author_facet Mingchen Xie (4325692)
Yahui Zhang (444739)
Haitao Wu (2411155)
Zeyu Wu (455882)
Hao Han (412732)
Xun Xie (15557433)
Rui Zhang (13940)
Jianhua Cheng (467464)
Jian Xu (31545)
author_role author
dc.creator.none.fl_str_mv Mingchen Xie (4325692)
Yahui Zhang (444739)
Haitao Wu (2411155)
Zeyu Wu (455882)
Hao Han (412732)
Xun Xie (15557433)
Rui Zhang (13940)
Jianhua Cheng (467464)
Jian Xu (31545)
dc.date.none.fl_str_mv 2025-09-04T05:32:09Z
dc.identifier.none.fl_str_mv 10.3389/fnut.2025.1649553.s001
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Table_1_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_docx/30049702
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Clinical and Sports Nutrition
triglyceride-glucose index
hyperglycemic crisis
critical care
machine learning
mortality prediction
dc.title.none.fl_str_mv Table 1_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.docx
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description Background<p>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 patients with DM and to construct a risk prediction model using machine-learning algorithms.</p>Methods<p>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 subjects with diabetes possessing computable TyG indices within 24 h 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.</p>Results<p>Among 4,098 critically ill patients with DM, 328 developed HCE. Patients with HCE 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.</p>Conclusion<p>Elevated TyG index shows a notable correlation with the occurrence of HCE and negative results in critically ill patients with DM. Advanced multivariate machine-learning models are adept at pinpointing patients at high risk, thereby facilitating prompt clinical action.</p>
eu_rights_str_mv openAccess
id Manara_07881952a3a8bcbc729d39c46f29d607
identifier_str_mv 10.3389/fnut.2025.1649553.s001
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30049702
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Table 1_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.docxMingchen Xie (4325692)Yahui Zhang (444739)Haitao Wu (2411155)Zeyu Wu (455882)Hao Han (412732)Xun Xie (15557433)Rui Zhang (13940)Jianhua Cheng (467464)Jian Xu (31545)Clinical and Sports Nutritiontriglyceride-glucose indexhyperglycemic crisiscritical caremachine learningmortality predictionBackground<p>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 patients with DM and to construct a risk prediction model using machine-learning algorithms.</p>Methods<p>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 subjects with diabetes possessing computable TyG indices within 24 h 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.</p>Results<p>Among 4,098 critically ill patients with DM, 328 developed HCE. Patients with HCE 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.</p>Conclusion<p>Elevated TyG index shows a notable correlation with the occurrence of HCE and negative results in critically ill patients with DM. Advanced multivariate machine-learning models are adept at pinpointing patients at high risk, thereby facilitating prompt clinical action.</p>2025-09-04T05:32:09ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.3389/fnut.2025.1649553.s001https://figshare.com/articles/dataset/Table_1_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_docx/30049702CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/300497022025-09-04T05:32:09Z
spellingShingle Table 1_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.docx
Mingchen Xie (4325692)
Clinical and Sports Nutrition
triglyceride-glucose index
hyperglycemic crisis
critical care
machine learning
mortality prediction
status_str publishedVersion
title Table 1_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.docx
title_full Table 1_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.docx
title_fullStr Table 1_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.docx
title_full_unstemmed Table 1_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.docx
title_short Table 1_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.docx
title_sort Table 1_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.docx
topic Clinical and Sports Nutrition
triglyceride-glucose index
hyperglycemic crisis
critical care
machine learning
mortality prediction