Diabetes, resulting from inadequate insulin production or utilization, causes extensive harm to the body. Existing diagnostic methods are often invasive and come with drawbacks, such as cost constraints. Although there are machine learning models like Classwise k Nearest Neighbor (CkNN) and General Regression Neural Network (GRNN), they struggle with imbalanced data and result in under-performance. Leveraging advancements in sensor technology and machine learning, we propose a non-invasive diabetes diagnosis using a Back Propagation Neural Network (BPNN) with batch normalization, incorporating data re-sampling and normalization for class balancing. Our method addresses existing challenges such as limited performance associated with traditional machine learning. Experimental results on three datasets show significant improvements in overall accuracy, sensitivity, and specificity compared to traditional methods. Notably, we achieve accuracies of 89.81% in Pima diabetes dataset, 75.49% in CDC BRFSS2015 dataset, and 95.28% in Mesra Diabetes dataset. This underscores the potential of deep learning models for robust diabetes diagnosis. See project website https://steve-zeyu-zhang.github.io/DiabetesDiagnosis/

翻译：糖尿病因胰岛素分泌不足或利用障碍，会对身体造成广泛损害。现有诊断方法通常具有侵入性，且存在成本限制等缺陷。尽管已有诸如分类k最近邻（CkNN）和广义回归神经网络（GRNN）等机器学习模型，但它们在处理不平衡数据时表现欠佳，导致性能不理想。借助传感器技术和机器学习的发展，我们提出一种非侵入式糖尿病诊断方法，该方法采用含批量归一化的反向传播神经网络（BPNN），并结合数据重采样与归一化来实现类别平衡。我们的方法解决了传统机器学习性能有限等现有挑战。在三个数据集上的实验结果表明，与传统方法相比，该方法在总体准确率、灵敏度和特异度方面均有显著提升。值得注意的是，我们在Pima糖尿病数据集、CDC BRFSS2015数据集和Mesra糖尿病数据集上分别取得了89.81%、75.49%和95.28%的准确率。这凸显了深度学习模型用于稳健糖尿病诊断的潜力。请访问项目网站：https://steve-zeyu-zhang.github.io/DiabetesDiagnosis/