Department of Pharmacy Practice, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal, Udupi District, Karnataka 576 104, India.
Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Udupi District, Karnataka 576 104, India.
Int J Med Inform. 2024 Oct;190:105546. doi: 10.1016/j.ijmedinf.2024.105546. Epub 2024 Jul 10.
Diabetic kidney disease (DKD) is a diabetic microvascular complication often characterized by an unpredictable progression. Hence, early detection and recognition of patients vulnerable to progression is crucial.
To develop a prediction model to identify the stages of DKD and the factors contributing to progression to each stage using machine learning.
A retrospective study was conducted in a South Indian tertiary care hospital and collected the details of patients diagnosed with DKD from January 2017 to January 2022. Bayesian optimization-based machine learning techniques such as classification and regression were employed. The model was developed with the help of an optimization framework that effectively balances classification, prediction accuracy, and explainability.
Of the 311 patients diagnosed with DKD, 227 were selected for the study. A system for predicting DKD has been created for a patient dataset utilizing a variety of machine-learning approaches. The eXtreme gradient (XG) Boost method excelled, achieving 88.75% accuracy, 88.57% precision, 91.4% sensitivity,100% specificity, and 89.49% F1-score. An interpretable data-driven method highlights significant features for early DKD diagnosis. The best explainable prediction model uses the XG Boost classifier, revealing serum uric acid, urea, phosphorous, red blood cells, calcium, and absolute eosinophil count as the major predictors influencing the progression of DKD. In the case of regression models, the gradient boost regressor performed the best, with an R score of 0.97.
Machine learning algorithms can effectively predict the stages of DKD and thus help physicians in providing patients with personalized care at the right time.
糖尿病肾病（DKD）是一种糖尿病微血管并发症，其进展通常具有不可预测性。因此，早期发现和识别易进展的患者至关重要。
使用机器学习开发一种预测模型，以识别 DKD 阶段和导致每个阶段进展的因素。
本研究为回顾性研究，在印度南部的一家三级护理医院进行，收集了 2017 年 1 月至 2022 年 1 月期间诊断为 DKD 的患者的详细信息。采用基于贝叶斯优化的机器学习技术（如分类和回归）。该模型是在一个有效的分类、预测准确性和可解释性之间进行平衡的优化框架的帮助下开发的。
在 311 例诊断为 DKD 的患者中，有 227 例被纳入研究。利用多种机器学习方法为患者数据集创建了预测 DKD 的系统。XG Boost 方法表现出色，达到了 88.75%的准确率、88.57%的精度、91.4%的敏感性、100%的特异性和 89.49%的 F1 分数。一种可解释的数据驱动方法突出了早期 DKD 诊断的重要特征。最佳的可解释预测模型使用 XG Boost 分类器，揭示血清尿酸、尿素、磷、红细胞、钙和绝对嗜酸性粒细胞计数是影响 DKD 进展的主要预测因子。在回归模型中，梯度提升回归器表现最佳，R 分数为 0.97。
机器学习算法可以有效地预测 DKD 的阶段，从而帮助医生在适当的时候为患者提供个性化的护理。
