EUVIMEDObjevte EUVIMED
Crossref

Assessment of Diabetes Risk in Patients With Hepatitis B: A Machine Learning Approach Integrating 11 Inflammatory and Immune Indicators

Zhisheng Cai, Jingtao Liu, Wenjie Zhang, Yutong Lu, Yumeng Su, Tengyue Zhang iD, Yangyi Zhang iD, Xiaochi Wang, Linyi Ye, Ying Tao, Junjie Liu iD

Diabetes/Metabolism Research and Reviews · 2026-07 · 42 (5)

DOI: 10.1002/dmrr.70193 ↗

At a glance

Journal article in Diabetes/Metabolism Research and Reviews, published online on 2026-07-09. Written by Zhisheng Cai and 10 co-authors. Institution: Jinjiang Municipal Hospital, Quanzhou, Fujian, China. Major MEDLINE topics: Machine Learning, Diabetes Mellitus, Inflammation, Biomarkers. 21 references.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Chronic hepatitis B virus (HBV) infection is associated with an increased risk of diabetes; however, early detection of diabetes remains challenging due to silent progression in early stages. Given that 30%–50% of diabetic patients develop severe complications such as cardiovascular disease, renal failure, and neuropathy, timely risk assessment is critical for prevention.

Methods

We developed a machine learning model using data from 14,287 HBV‐positive adults across eight NHANES cycles (2003–2018) to identify diabetes. Eleven inflammation‐immune composite indicators were integrated with demographic and biochemical parameters. Following LASSO variable selection and a 7:3 train‐test split, seven algorithms were compared. Model performance was evaluated using the area under the ROC curve (AUC), calibration curve, and decision curve analysis (DCA).

Results

The Artificial Neural Network (ANN) emerged as the optimal model for diabetes risk assessment. It achieved an AUC of 0.83 (95% CI: 0.80–0.85) and an accuracy of 82% (95% CI: 0.79–0.85). SHAP analysis identified age and UHR as the most influential predictors, while HRR showed significant protective effects.

Conclusion

This study presents a robust, interpretable model for diabetes risk assessment in HBV patients that integrates novel inflammation‐immune composite indicators. These findings highlight the model's utility as a potential clinical tool for screening individuals with undiagnosed diabetes.

Subjects

MeSH terms (MEDLINE)

Machine LearningDiabetes MellitusInflammationBiomarkersHepatitis B, ChronicHumansFemaleMaleRisk AssessmentRisk FactorsMiddle AgedPrognosisAdultPredictive Learning ModelsNeural Networks, ComputerHepatitis B virusFollow-Up Studies

Author keywords

SHAPdiabeteshepatitis Binflammatory immune factorsmachine learning

Substances

Biomarkers

Authors and institutions

  • Jinjiang Municipal Hospital, Quanzhou, Fujian, China.
  • School of Basic Medical Sciences, China Three Gorges University, Yichang, China.

ORCID profiles: Tengyue Zhang, Yangyi Zhang, Junjie Liu

Cite

APA

Cai, Z., Liu, J., Zhang, W., Lu, Y., Su, Y., Zhang, T., Zhang, Y., Wang, X., Ye, L., Tao, Y., & Liu, J. (2026). Assessment of Diabetes Risk in Patients With Hepatitis B: A Machine Learning Approach Integrating 11 Inflammatory and Immune Indicators. Diabetes/Metabolism Research and Reviews, 42(5). https://doi.org/10.1002/dmrr.70193

Vancouver

Cai Z, Liu J, Zhang W, Lu Y, Su Y, Zhang T, et al. Assessment of Diabetes Risk in Patients With Hepatitis B: A Machine Learning Approach Integrating 11 Inflammatory and Immune Indicators. Diabetes/Metabolism Research and Reviews. 2026;42(5). doi:10.1002/dmrr.70193

BibTeX
@article{Cai2026,
  author = {Cai, Zhisheng and Liu, Jingtao and Zhang, Wenjie and Lu, Yutong and Su, Yumeng and Zhang, Tengyue and Zhang, Yangyi and Wang, Xiaochi and Ye, Linyi and Tao, Ying and Liu, Junjie},
  title = {Assessment of Diabetes Risk in Patients With Hepatitis B: A Machine Learning Approach Integrating 11 Inflammatory and Immune Indicators},
  journal = {Diabetes/Metabolism Research and Reviews},
  year = {2026},
  volume = {42},
  number = {5},
  doi = {10.1002/dmrr.70193}
}
Start for free →