Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, 30332, GA, USA; Department of Biomedical Informatics, Emory University, Atlanta, 30322, GA, USA; Department of Biomedical Engineering, Duke University, Durham, 27708, NC, USA.
Department of Pediatrics, Emory University, Atlanta, 30322, GA, USA.
Comput Biol Med. 2024 Dec;183:109255. doi: 10.1016/j.compbiomed.2024.109255. Epub 2024 Oct 16.
Continuous Glucose Monitoring (CGM) provides a detailed representation of glucose fluctuations in individuals, offering a rich dataset for understanding glycemic control in diabetes management. This study explores the potential of Riemannian manifold-based geometric clustering to analyze and interpret CGM data for individuals with Type 1 Diabetes (T1D) and healthy controls (HC), aiming to enhance diabetes management and treatment personalization.
We utilized CGM data from publicly accessible datasets, covering both T1D individuals on insulin and HC. Data were segmented into daily intervals, from which 27 distinct glycemic features were extracted. Uniform Manifold Approximation and Projection (UMAP) was then applied to reduce dimensionality and visualize the data, with model performance validated through correlation analysis between Silhouette Score (SS) against HC cluster and HbA1c levels.
UMAP effectively distinguished between T1D on daily insulin and HC groups, with data points clustering according to glycemic profiles. Moderate inverse correlations were observed between SS against HC cluster and HbA1c levels, supporting the clinical relevance of the UMAP-derived metric.
This study demonstrates the utility of UMAP in enhancing the analysis of CGM data for diabetes management. We revealed distinct clustering of glycemic profiles between healthy individuals and diabetics on daily insulin indicating that in most instances insulin does not restore a normal glycemic phenotype. In addition, the SS quantifies day by day the degree of this continued dysglycemia and therefore potentially offers a novel approach for personalized diabetes care.
连续血糖监测（CGM）提供了个体血糖波动的详细描述，为理解糖尿病管理中的血糖控制提供了丰富的数据集。本研究探讨了基于黎曼流形的几何聚类在分析和解释 1 型糖尿病（T1D）患者和健康对照（HC）CGM 数据方面的潜力，旨在增强糖尿病管理和治疗的个性化。
我们利用了公开可获得的数据集的 CGM 数据，涵盖了胰岛素治疗的 T1D 个体和 HC。数据被分段为每日间隔，从中提取了 27 个不同的血糖特征。然后应用统一流形逼近和投影（UMAP）来降低维度并可视化数据，通过 Silhouette 得分（SS）与 HC 簇和 HbA1c 水平的相关性分析验证模型性能。
UMAP 有效地区分了 T1D 患者在胰岛素治疗日和 HC 组之间的差异，数据点根据血糖谱聚类。观察到 SS 与 HC 簇和 HbA1c 水平之间存在中度的负相关，支持 UMAP 衍生指标的临床相关性。
本研究表明 UMAP 在增强 CGM 数据在糖尿病管理中的分析方面具有实用性。我们揭示了健康个体和接受胰岛素治疗的糖尿病患者之间的血糖谱聚类明显不同，表明在大多数情况下，胰岛素并不能恢复正常的血糖表型。此外，SS 量化了这种持续的血糖异常的程度，因此可能为个性化的糖尿病护理提供了一种新方法。
