Understanding the complex relationships of biomarkers in diabetes is pivotal
for advancing treatment strategies, a pressing need in diabetes research. This
study applies Bayesian network structure learning to analyze the Shanghai Type
1 and Type 2 diabetes mellitus datasets, revealing complex relationships among
key diabetes-related biomarkers. The constructed Bayesian network presented
notable predictive accuracy, particularly for Type 2 diabetes mellitus, with
root mean squared error (RMSE) of 18.23 mg/dL, as validated through
leave-one-domain experiments and Clarke error grid analysis. This study not
only elucidates the intricate dynamics of diabetes through a deeper
understanding of biomarker interplay but also underscores the significant
potential of integrating data-driven and knowledge-driven methodologies in the
realm of personalized diabetes management. Such an approach paves the way for
more custom and effective treatment strategies, marking a notable advancement
in the field.

通过应用贝叶斯网络结构学习分析上海 1 型和 2 型糖尿病数据集，揭示了与糖尿病相关的关键生物标志物之间的复杂关系。构建的贝叶斯网络在预测准确性方面表现出显著的效果，特别是对于 2 型糖尿病，其均方根误差为 18.23 毫克 / 分升，在单域实验证实和克拉克误差网格分析中得到了验证。这项研究不仅通过深入理解生物标志物的相互作用，阐明了糖尿病的复杂动态，而且强调了将数据驱动和知识驱动方法结合在个性化糖尿病管理领域的巨大潜力。这种方法为更加定制和有效的治疗策略铺平了道路，标志着该领域的显著进展。