通过多种机器学习算法在老年人脂肪组织中识别2型糖尿病的潜在生物标志物
Yun-Sang Yu1, Da Som Lee1, Joo Hyun Lim1
1Division of Endocrine and Kidney Disease Research, Department of Chronic Disease Convergence Research, National Institute of Health, Cheongju, 28159, Korea.
Scientific reports
|December 30, 2025
概括
新的生物标志物AIM2和FHOD3在老年人中显示出早期2型糖尿病 (T2D) 诊断的前景. 这些发现可能会导致这种人群中糖尿病的新诊断和治疗策略.
科学领域:
- 基因组学就是基因组学.
- 代谢疾病 代谢疾病
- 衰老研究研究 衰老研究
背景情况:
- 与年龄相关的脂肪组织功能障碍会损害胰岛素敏感性并促进炎症,导致老年人患2型糖尿病 (T2D).
- 在老年人群中早期诊断T2D对于有效管理和预防并发症至关重要.
研究的目的:
- 在老年人中确定T2D诊断的新生物标志物.
- 利用机器学习和基因表达数据开发T2D的预测工具.
主要方法:
- 对腹部皮下脂肪组织基因表达数据集的综合转录组分析.
- 应用批量效应校正和差异基因表达 (DEG) 分析.
- 使用LASSO,支持矢量机-递归特征消除 (SVM-RFE) 和随机森林算法来选择生物标志物.
- 执行接收器运行特征 (ROC) 曲线分析以评估预测性能.
主要成果:
- 鉴定了210个差异表达基因 (DEGs),主要丰富于炎症和免疫通路.
- 始终确定AIM2和FHOD3为最佳生物标志物,可以区分T2D和非T2D的老年人.
- 使用ROC曲线分析,证明了AIM2和FHOD3的高预测性能.
结论:
- 在老年人中,AIM2和FHOD3是早期T2D诊断的潜在新生物标志物.
- 这些基因可能代表了在老年人群中管理糖尿病的有价值的诊断和治疗标.
相关概念视频
Type II Diabetes I: Introduction
Type 2 diabetes mellitus (T2DM) is a chronic metabolic disorder characterized by insulin resistance, in which target tissues such as the liver, muscle, and adipose tissue respond poorly to insulin. It is also associated with inadequate compensatory insulin secretion, where pancreatic β-cells fail to produce sufficient insulin. Together, these abnormalities lead to persistent hyperglycemia.EtiologyT2DM develops through a complex interaction of genetic predisposition and environmental or...
Type II Diabetes II: Pathophysiology
PathophysiologyType 2 diabetes mellitus (T2DM ) is a chronic metabolic disorder characterized by insulin resistance and progressive pancreatic β-cell dysfunction, leading to impaired glucose homeostasis. It results from interactions among genetic predisposition, environmental factors, and metabolic stressors, such as overnutrition and a sedentary lifestyle.Insulin Resistance and Glucose DysregulationEarly T2DM involves insulin resistance in skeletal muscle, adipose tissue, and the liver.


