Department of Mathematics and Computer Sciences, Balearic Islands University, Palma, Spain.
Institut d'Investigació Sanitària Illes Balears (IdISBa), Hospital Universitari Son Espases, Palma, Spain.
Front Public Health. 2023 Jan 12;10:1035025. doi: 10.3389/fpubh.2022.1035025. eCollection 2022.
It is known that people with prediabetes increase their risk of developing type 2 diabetes (T2D), which constitutes a global public health concern, and it is associated with other diseases such as cardiovascular disease.
This study aimed to determine those factors with high influence in the development of T2D once prediabetes has been diagnosed, through a Bayesian network (BN), which can help to prevent T2D. Furthermore, the set of features with the strongest influences on T2D can be determined through the . A BN model for T2D was built from a dataset composed of 12 relevant features of the T2D domain, determining the dependencies and conditional independencies from empirical data in a multivariate context. The structure and parameters were learned with the bnlearn package in R language introducing knowledge. The was considered to find those features (variables) which increase the risk of T2D.
The BN model established the different relationships among features (variables). Through inference, a high estimated probability value of T2D was obtained when the body mass index (BMI) was instantiated to value, the glycosylated hemoglobin (HbA1c) to more than 6 value, the fatty liver index (FLI) to more than 60 value, physical activity (PA) to state, and age to 48-62 state. The features increasing T2D in specific states (warning factors) were ranked.
The feasibility of BNs in epidemiological studies is shown, in particular, when data from T2D risk factors are considered. BNs allow us to order the features which influence the most the development of T2D. The proposed BN model might be used as a general tool for prevention, that is, to improve the prognosis.
已知糖尿病前期患者会增加患 2 型糖尿病（T2D）的风险，这是一个全球性的公共卫生问题，并且与心血管疾病等其他疾病有关。
本研究旨在通过贝叶斯网络（BN）确定一旦诊断出糖尿病前期，哪些因素对 T2D 的发展影响最大，从而有助于预防 T2D。此外，还可以通过确定对 T2D 影响最强的特征集。从包含 T2D 领域 12 个相关特征的数据集构建 T2D 的 BN 模型，在多变量环境中确定从经验数据中得出的依赖关系和条件独立性。使用 R 语言中的 bnlearn 包学习结构和参数，引入知识。使用 来寻找增加 T2D 风险的特征（变量）。
BN 模型建立了特征（变量）之间的不同关系。通过推理，当身体质量指数（BMI）实例化为 值、糖化血红蛋白（HbA1c）超过 6 值、脂肪肝指数（FLI）超过 60 值、体力活动（PA）处于 状态并且年龄处于 48-62 状态时，T2D 的估计概率值很高。按特定状态（警告因素）排列增加 T2D 的特征。
贝叶斯网络在流行病学研究中的可行性得到了证明，特别是当考虑到 T2D 危险因素的数据时。贝叶斯网络允许我们对影响 T2D 发展的特征进行排序。所提出的 BN 模型可以用作预防的一般工具，即改善预后。
