Department of Information Sciences and Technology, Yanshan University, Hebei, China.
Department of Economics and Management, Yanshan University, Hebei, China.
Sci Rep. 2019 Jul 12;9(1):10103. doi: 10.1038/s41598-019-46631-9.
The increasing ratio of diabetes is found risky across the planet. Therefore, the diagnosis is important in population with extreme risk of diabetes. In this study, a decision-making classifier (J48) is applied over a data-mining platform (Weka) to measure accuracy and linear regression on classification results to forecast cost/benefit ratio in diabetes mellitus patients along with prevalence. In total 108 invasive and non-invasive medical features are considered from 251 patients for assessment, and the real-time data are gathered from Pakistan over a time span of June 2017 to April 2018. The results indicate that J48 classifiers achieved the best accuracy of (99.28%), whereas, error rate (0.08%), Kappa stats, PRC, and MCC are (0.98%), precision, recall, and F-matrix are (0.99%). In addition, true positive rate is (0.99%) and false positive is (0.08%). The regression forecast decision indicates blood pressure and glucose level are key features for diabetes. The cost/benefit matrix indicates two predictions for positive test with accuracy (66.68%) and (30.60%), and key attributes with total Gain (118.13%). The study confirmed the proposed prediction is practical for screening of diabetes mellitus patients at the initial stage without invasive medical tests and found effectual in the early diagnosis of diabetes.
全球范围内糖尿病的发病率不断上升，因此，对于糖尿病高危人群的诊断非常重要。在这项研究中，我们在数据挖掘平台（Weka）上应用决策分类器（J48）来衡量分类结果的准确性，并进行线性回归，以预测糖尿病患者的成本/效益比和患病率。总共从 251 名患者中考虑了 108 个侵袭性和非侵袭性的医学特征进行评估，实时数据是 2017 年 6 月至 2018 年 4 月期间从巴基斯坦收集的。结果表明，J48 分类器达到了最佳的准确性（99.28%），而错误率（0.08%）、Kappa 统计量、PRC 和 MCC 分别为（0.98%）、精度、召回率和 F 矩阵分别为（0.99%）。此外，真阳性率为（0.99%），假阳性率为（0.08%）。回归预测决策表明，血压和血糖水平是糖尿病的关键特征。成本/效益矩阵表明，阳性测试的两种预测准确性分别为（66.68%）和（30.60%），总增益（118.13%）的关键属性。该研究证实了所提出的预测在没有侵袭性医学测试的情况下，对于糖尿病患者的早期筛查是实用的，并且在糖尿病的早期诊断中是有效的。
