Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Dec;57(1):2536204.
doi: 10.1080/07853890.2025.2536204. Epub 2025 Jul 25.

Integrated machine learning and population attributable fraction analysis of systemic inflammatory indices for mortality risk prediction in diabetes and prediabetes

Zixi Zhang  1 , Chenyang Li  2 , Yichao Xiao  1 , Chan Liu  3 , Xiaoqin Luo  4 , Cancan Wang  5 , Yongguo Dai  6 , Qiuzhen Lin  1 , Zeying Zhang  7 , Cheng Zheng  2 , Jiafeng Lin  2 , Tao Tu  1 , Qiming Liu  1
Affiliations

Integrated machine learning and population attributable fraction analysis of systemic inflammatory indices for mortality risk prediction in diabetes and prediabetes

Zixi Zhang et al. Ann Med. 2025 Dec.

Abstract

Background: Chronic systemic inflammation is a key contributor to cardiometabolic complications in diabetes mellitus (DM) and prediabetes (PreDM). Composite inflammatory indices-including neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), systemic inflammation response index (SIRI), systemic immune-inflammation index (SII), platelet-to-hemoglobin ratio (PHR), and aggregate inflammation systemic index (AISI)-have shown prognostic value for mortality. However, their integrated assessment using machine learning and quantification at the population level remain limited.

Methods: In this retrospective cohort study, 11,304 adults with DM or PreDM from the National Health and Nutrition Examination Survey (NHANES, 2005-2018) were analyzed. The primary outcomes were all-cause and cardiovascular mortality. Associations between inflammatory indices and mortality were evaluated using Cox proportional hazards models. Predictive performance was assessed via Extreme Gradient Boosting (XGBoost), and population attributable fractions (PAFs) estimated the mortality burden related to systemic inflammation.

Results: NLR, MLR, SIRI, SII, and AISI were independently associated with all-cause and cardiovascular mortality. MLR showed the strongest association (HR: 2.948 and 3.717 for all-cause and CVD mortality, respectively). XGBoost identified SIRI, SII, AISI, MLR, and NLR as key predictors, with SIRI ranked highest for cardiovascular mortality. Inclusion of inflammatory indices improved model discrimination and calibration. PAF analysis suggested that 10-20% of mortality reduction could be attributed to improved inflammatory profiles.

Conclusion: Systemic inflammatory indices are independent predictors of mortality in individuals with DM or PreDM. Their integration into machine learning models enhances risk prediction and may inform population-level strategies for cardiometabolic risk stratification.

Keywords: Diabetes mellitus; mortality; national health and nutrition examination survey; population attributable fraction; prediabetes; systemic inflammatory indices.

Plain language summary

What is currently known about this topic?Chronic inflammation contributes to the progression of DM or PreDM.Traditional inflammatory markers are costly and less accessible for widespread screenings.Systemic inflammatory indices provide an easily accessible alternative for diagnosis and prognosis.What is the key research question?How does machine learning improve mortality risk prediction, and how does population attributable fraction quantify the contribution of systemic inflammatory indices?What is new?Systemic inflammatory indices are independently associated with mortality in DM or PreDM.Machine learning identifies systemic inflammatory indices as key predictors of mortality.Improving systemic inflammatory indices could reduce mortality events by approximately 10–20%.How might this study influence clinical practice?Integrating systemic inflammatory indices improves risk stratification, and anti-inflammatory strategies may reduce mortality.

PubMed Disclaimer

Conflict of interest statement

There are no conflicts of interest or competing interests.

Figures

Figure 1.
Figure 1.
K–M Survival curves for all-cause mortality among systemic inflammatory indices. AISI, aggregate index of systemic inflammation; K–M, Kaplan–Meier; MLR, monocyte-to-lymphocyte ratio; NLR, neutrophil-to-lymphocyte ratio; PHR, platelet-to-high-density lipoprotein cholesterol ratio; SII, systemic immune-inflammation index; SIRI, systemic inflammation response index.
Figure 2.
Figure 2.
Associations between systemic inflammatory indices and all-cause mortality in patients with DM or PreDM. AISI, aggregate index of systemic inflammation; CI, confidence interval; DM, diabetes mellitus; HR, hazard ratio; MLR, monocyte-to-lymphocyte ratio; NLR, neutrophil-to-lymphocyte ratio; PHR, platelet-to-high-density lipoprotein cholesterol ratio; PreDM, prediabetes; SII, systemic immune-inflammation index; SIRI, systemic inflammation response index.
Figure 3.
Figure 3.
Feature selection for all-cause and cardiovascular mortality using the Boruta algorithm and LASSO regression analysis. A: Boruta algorithm and all-cause mortality; B: Boruta algorithm and cardiovascular mortality; C: LASSO regression analysis and all-cause mortality; D: LASSO regression analysis and cardiovascular mortality. AISI, aggregate index of systemic inflammation; ALB, albumin; ALT, alanine aminotransferase; AST, aspartate aminotransferase; BMI, body mass index; CHD, coronary heart disease; CHF, congestive heart failure; DBP, diastolic blood pressure; DM, diabetes mellitus; eGFR, estimated glomerular filtration rate; FPG, fasting plasma glucose; Hb, hemoglobin; HbA1c, glycosylated hemoglobin; HTN, hypertension; LASSO, least absolute shrinkage and selection operator; LDL-C, low-density lipoprotein cholesterol; MLR, monocyte-to-lymphocyte ratio; NLR, neutrophil-to-lymphocyte ratio; PHR, platelet-to-high-density lipoprotein cholesterol ratio; PreDM, prediabetes; RBC, red blood cell; SBP, systolic blood pressure; SII, systemic immune-inflammation index; SIRI, systemic inflammation response index; TC, total cholesterol; TG, triglyceride; UA, uric acid.
Figure 4.
Figure 4.
Feature importance of seven predictive models for all-cause mortality. A: Basic model; B: Basic model + SII; C: Basic model + SIRI; D: Basic model + AISI; E: Basic model + MLR; F: Basic model + NLR; G: Basic model + PHR. AISI, aggregate index of systemic inflammation; ALB, albumin; AST, aspartate aminotransferase; CHF, congestive heart failure; DM, diabetes mellitus; eGFR, estimated glomerular filtration rate; FPG, fasting plasma glucose; MLR, monocyte-to-lymphocyte ratio; NLR, neutrophil-to-lymphocyte ratio; PHR, platelet-to-high-density lipoprotein cholesterol ratio; RBC, red blood cell; SII, systemic immune-inflammation index; SIRI, systemic inflammation response index.
Figure 5.
Figure 5.
Feature importance of seven predictive models for cardiovascular mortality. A: Basic model; B: Basic model + SII; C: Basic model + SIRI; D: Basic model + AISI; E: Basic model + MLR; F: Basic model + NLR; G: Basic model + PHR. AISI, aggregate index of systemic inflammation; AST, aspartate aminotransferase; eGFR, estimated glomerular filtration rate; MLR, monocyte-to-lymphocyte ratio; NLR, neutrophil-to-lymphocyte ratio; PHR, platelet-to-high-density lipoprotein cholesterol ratio; RBC, red blood cell; SII, systemic immune-inflammation index; SIRI, systemic inflammation response index.
Figure 6.
Figure 6.
Predictive performance of the original and six modified models. A–F: All-cause mortality. G–L: Cardiovascular mortality. AISI, aggregate index of systemic inflammation; AUC, area under the receiver operating characteristic curve; MLR, monocyte-to-lymphocyte ratio; NLR, neutrophil-to-lymphocyte ratio; PHR, platelet-to-high-density lipoprotein cholesterol ratio; SII, systemic immune-inflammation index; SIRI, systemic inflammation response index.
See this image and copyright information in PMC

References

    1. Sun H, Saeedi P, Karuranga S, et al. IDF diabetes atlas: global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045. Diabetes Res Clin Pract. 2022;183:109119. doi: 10.1016/j.diabres.2021.109119. - DOI - PMC - PubMed
    1. (NCD-RisC) NRFC . Worldwide trends in diabetes prevalence and treatment from 1990 to 2022: a pooled analysis of 1108 population-representative studies with 141 million participants. Lancet (London, England). 2024;404(10467):2077–2093. - PMC - PubMed
    1. Parker ED, Lin J, Mahoney T, et al. Economic costs of diabetes in the U.S. in 2022. Diabetes Care. 2024;47(1):26–43. doi: 10.2337/dci23-0085. - DOI - PubMed
    1. Bommer C, Heesemann E, Sagalova V, et al. The global economic burden of diabetes in adults aged 20–79 years: a cost-of-illness study. Lancet Diabet Endocrinol. 2017;5(6):423–430. - PubMed
    1. Gregg EW, Pratt A, Owens A, et al. The burden of diabetes-associated multiple long-term conditions on years of life spent and lost. Nat Med. 2024;30(10):2830–2837. doi: 10.1038/s41591-024-03123-2. - DOI - PMC - PubMed

MeSH terms