Multicenter Evaluation of Prognostic Nutritional Index and Systemic Immune-Inflammation Index in Predicting Mortality Among Critically Ill Cardiovascular and Cerebrovascular Patients With Varied Glucose Metabolism - A Machine Learning-Based Cohort Study

Aug 5, 2026

Critically ill patients with cardiovascular and cerebrovascular diseases face high mortality risk, yet existing prognostic models inadequately address glucose-metabolic subgroups. A retrospective, multicenter, machine learning cohort study evaluates whether combining the Prognostic Nutritional Index (PNI) and the Systemic Immune-Inflammation Index (SII) improves mortality prediction across glucose regulation categories. Cox regression, Kaplan–Meier, and ROC analyses assess associations, discrimination, and external generalizability using an independent Chinese cohort.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Methods

Results

Mortality prediction performance

Discussion

Conclusion

OPEN ACCESS EDITED BY Ricardo Cleto Marinho, Santo António Local Health Unit, Portugal REVIEWED BY Laura Avila-Jimenez, Mexican Social Security Institute, Mexico Xiao Dong Song, First Affiliated Hospital of Chongqing Medical University, China *CORRESPONDENCE Shujie Huang [huangsj3.thaa@vip.163.com](huangsj3.thaa@vip.163.com)[ ](huangsj3.thaa@vip.163.com)Jianhua Cheng [cjh19940317@163.com](cjh19940317@163.com) †These authors have contributed equally to this work and share first authorship RECEIVED 11 September 2025 REVISED 17 December 2025 ACCEPTED 13 January 2026 PUBLISHED 03 February 2026 CITATION Li Z, Xie M, Wu H, Wang T, Huang S and Cheng J (2026) Multicenter evaluation of prognostic nutritional index and systemic immune-inflammation index in predicting mortality among critically ill cardiovascular and cerebrovascular patients with varied glucose metabolism: a machine learning-based cohort study. Front. Nutr. 13:1703589. doi: 10.3389/fnut.2026.1703589 COPYRIGHT © 2026 Li, Xie, Wu, Wang, Huang and Cheng. 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) and the copyright owner(s) 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. TYPE Original Research PUBLISHED 03 February 2026 DOI 10.3389/fnut.2026.1703589 Multicenter evaluation of prognostic nutritional index and systemic immune-inflammation index in predicting mortality among critically ill cardiovascular and cerebrovascular patients with varied glucose metabolism: a machine learning-based cohort study Zhimin Li 1, 2†, Mingchen Xie 1†, Haitao Wu 1, Tingxuan Wang 1, Shujie Huang3* and Jianhua Cheng 1* 1Department of Neurosurgery, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China, 2Department of Critical Care Medicine, Jishuitan Hospital, Beijing, China, 3Department of Vascular Surgery, Qingdao Hospital, University of Health and Rehabilitation Sciences (Qingdao Municipal Hospital), Qingdao, Shandong, China Background: Critically ill patients with cardiovascular and cerebrovascular diseases face high mortality risks, necessitating precise prognostic tools. Current models lack granularity in assessing glucose metabolic subgroups, while isolated use of the Prognostic Nutritional Index (PNI) and Systemic ImmuneInflammation Index (SII) has limitations. This study evaluates their combined predictive value for mortality across glucose metabolic profiles using machine learning. Methods: We conducted a retrospective cohort study of 1,698 patients from the MIMIC-IV database (2008–2019), stratified by glucose metabolic status: normal glucose regulation (NGR), prediabetes (Pre-DM), and diabetes mellitus (DM) . Prognostic associations and discrimination performance were evaluated using Cox regression, Kaplan–Meier analysis, and ROC curves. Machine learning models—including logistic regression, decision tree, random forest, XGBoost, and LightGBM—were developed based on Boruta-selected features to predict 28-day and 90-day all-cause mortality. Model performance was assessed using AUC, accuracy, and F1-score. To externally validate the machine learning models, we incorporated an independent cohort of critically ill cardiovascular and cerebrovascular patients (n = 1,194) from two tertiary hospitals in China: The Affiliated Hospital of Qingdao University and Qingdao Municipal Hospital. Results: Higher PNI was associated with reduced mortality, whereas elevated SII predicted higher mortality risk. The combined PNI-SII model outperformed individual indices across glucose subgroups, showing the best performance in Pre-DM patients (AUC = 0.775 for 28-day mortality) . PNI’s protective effect was atte

FAQs

What clinical problem does the study address?

It targets the need for more precise mortality prediction in critically ill cardiovascular and cerebrovascular patients, particularly across different glucose metabolism profiles.

How are glucose metabolic subgroups defined for analysis?

Patients are stratified into normal glucose regulation (NGR), prediabetes (Pre-DM), and diabetes mellitus (DM).

What is the study’s main finding about PNI and SII?

Higher PNI is associated with lower mortality, while higher SII predicts higher mortality risk; the combined PNI-SII model outperforms individual indices, with the best performance in the Pre-DM group.

Aug 5, 2026

Upload by Valentina