What question did this study set out to answer?

The research aims to identify biomarkers associated with type 2 diabetes in older adults and develop a predictive tool for diagnosis.

January 10, 2026Scientific Reports0 citationsOpen Access

Identifying potential biomarkers for type 2 diabetes in the adipose tissue of older adults via multiple machine learning algorithms

YYYun-Sang YuKorea National Institute of Health DLDa Som Lee JLJoo Hyun LimSeoul National University Hospital

Key Result

AIM2 and FHOD3 were identified as optimal biomarkers for distinguishing older adults with type 2 diabetes, showing high predictive performance in ROC analysis.

Key Points

The research aims to identify biomarkers associated with type 2 diabetes in older adults and develop a predictive tool for diagnosis.
Integrated transcriptomic analysis and machine learning techniques.
Obtain gene expression datasets from the Gene Expression Omnibus (GEO) database.
Conduct differentially expressed gene (DEG) analysis and batch effect correction.
Utilize LASSO, SVM-RFE, and random forest algorithms to extract predictive genes.
Identified 210 differentially expressed genes (DEGs) related to inflammation and immune pathways.
Two genes, AIM2 and FHOD3, consistently distinguished older adults with and without type 2 diabetes.
Receiver operating characteristic (ROC) analysis showed high predictive performance for these biomarkers.

Structured PICO

Can machine learning algorithms identify reliable transcriptomic biomarkers for type 2 diabetes in the adipose tissue of older adults?

Population

Transcriptomic datasets of abdominal subcutaneous adipose tissue from older adults with and without type 2 diabetes (n=31 total; 20 in training set, 11 in test set) from GEO databases, and male C57BL/6 mice (3 and 18 months old, n=10-12 per group) on normal or high-fat diet.

Intervention

Machine learning algorithms (LASSO logistic regression, SVM-RFE, and random forest) applied to transcriptomic data to identify diagnostic biomarkers.

Comparator

Older healthy adults without type 2 diabetes.

Outcome

Identification of optimal diagnostic biomarkers for distinguishing older adults with type 2 diabetes from those without.surrogate

Machine learning analysis of adipose tissue transcriptomics identified AIM2 and FHOD3 as highly accurate potential biomarkers for type 2 diabetes in older adults.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Abstract Age-related decline in adipose tissue function is closely associated with impaired insulin sensitivity and chronic low-grade inflammation, and these conditions contribute to type 2 diabetes (T2D) development in older adults. Therefore, reliable biomarkers may be helpful for early T2D diagnosis in older adults. We aimed to identify novel biomarkers linked to diabetes in older adults and to develop a predictive tool for diabetes diagnosis. We integrated transcriptomic analysis and machine learning to screen key genes associated with T2D in older adults. Gene expression datasets related to abdominal subcutaneous adipose tissue were obtained from the Gene Expression Omnibus (GEO) database. Through batch effect correction and differentially expressed gene (DEG) analysis of the combined dataset, 210 DEGs were identified. Functional enrichment analysis revealed that these DEGs were enriched mainly in inflammation- and immune-associated pathways. To extract T2D-predictive genes, we used three machine learning algorithms: LASSO, SVM-RFE and random forest. Two common genes, AIM2 and FHOD3, were consistently identified as the optimal biomarkers for distinguishing older adults with T2D from those without T2D. Receiver operating characteristic (ROC) curve analysis revealed high predictive performance. AIM2 and FHOD3 could serve as novel diagnostic and therapeutic targets for older adults with diabetes.

Ask AI

Helpful

Bookmark

View Full Paper