Family Medicine, King Abdulaziz Medical City, King Abdullah International Medical Research Center, Riyadh, Kingdom of Saudi Arabia.
Department of Health Informatics, College of Public Health and Health Informatics, King Saud bin Abdul-Aziz University for Health Sciences, Riyadh, Saudi Arabia.
Medicine (Baltimore). 2022 Jul 22;101(29):e29588. doi: 10.1097/MD.0000000000029588.
Saudi Arabia ranks 7th globally in terms of diabetes prevalence, and its prevalence is expected to reach 45.36% by 2030. The cost of diabetes is expected to increase to 27 billion Saudi riyals in cases where undiagnosed individuals are also documented. Prevention and early detection can effectively address these challenges.
To improve healthcare services and assist in building predictive models to estimate the probability of diabetes in patients.
A chart review, which was a retrospective cohort study, was conducted at the National Guard Health Affairs in Riyadh, Saudi Arabia. Data were collected from 5 hospitals using National Guard Health Affairs databases. We used 38 attributes of 21431 patients between 2015 and 2019. The following phases were performed: (1) data collection, (2) data preparation, (3) data mining and model building, and (4) model evaluation and validation. Subsequently, 6 algorithms were compared with and without the synthetic minority oversampling technique.
The highest performance was found in the Bayesian network, which had an area under the curve of 0.75 and 0.71.
Although the results were acceptable, they could be improved. In this context, missing data owing to technical issues played a major role in affecting the performance of our model. Nevertheless, the model could be used in prevention, health monitoring programs, and as an automated mass population screening tool without the need for extra costs compared to traditional methods.
沙特阿拉伯的糖尿病患病率在全球排名第 7 位，预计到 2030 年将达到 45.36%。如果将未确诊的患者也计算在内，糖尿病的成本预计将增加到 270 亿沙特里亚尔。预防和早期发现可以有效地解决这些挑战。
改善医疗保健服务，并协助构建预测模型，以估计患者患糖尿病的概率。
这是一项在沙特阿拉伯利雅得的沙特阿拉伯国民警卫队卫生事务署进行的图表回顾性队列研究。数据是从 5 家医院使用沙特阿拉伯国民警卫队卫生事务署数据库收集的。我们使用了 21431 名患者的 38 个属性，时间范围是 2015 年至 2019 年。研究分为以下四个阶段：（1）数据收集，（2）数据准备，（3）数据挖掘和模型构建，（4）模型评估和验证。随后，我们比较了 6 种算法在有无合成少数过采样技术时的表现。
贝叶斯网络的性能最高，曲线下面积为 0.75 和 0.71。
尽管结果可以接受，但仍有改进的空间。在这种情况下，由于技术问题导致的数据缺失对模型的性能产生了重大影响。然而，与传统方法相比，该模型可以用于预防、健康监测计划，以及作为一种自动的大规模人群筛查工具，而无需额外的成本。
