Diabetes mellitus and its complication such as heart disease, stroke, kidney failure, etc. is a serious concern all over the world. Hence, monitoring some important blood parameters non-invasively is of utmost importance, that too with high accuracy. This paper presents an in-house developed system, which will be helpful for diabetes patients with Chronic Kidney Disease (CKD) to monitor blood urea and glucose. This manuscript discusses a comparative study for the prediction of blood urea and glucose using Backpropagation Artificial Neural Network (BP- ANN) and Partial Least Square Regression (PLSR) model. The NVIDIA Jetson Nano board controls the five fixed LED wavelengths in the Near Infrared (NIR) region from $2.0~\mu \text{m}$ to $2.5~\mu \text{m}$ with a constant emission power of 1.2 mW. The spectra for 57 laboratory prepared samples conforming with major blood constituents of the blood sample were recorded. From these samples, 53 spectra were used for training/calibration of the BP-ANN/PLSR model and the remaining 4 samples were used for validating the model. The PLSR model predicts blood urea and glucose with a Root Mean Square Error (RMSE) of 0.88 & 12.01 mg/dL, Coefficient of Determination R ² = 0.93 & R ² = 0.97, Accuracy of 94.2 % and 90.14 %, respectively. To improve the prediction accuracy, BP-ANN model is applied. Later the Principal Component Analysis (PCA) technique was applied to these 57 spectra values. These PCA values were used to train and validate the BP-ANN model. After applying the BP-ANN model, the prediction of blood urea & glucose improved remarkably, which achieved RMSE of 0.69 mg/dL, R ² = 0.96, Accuracy of 95.96 % for urea and RMSE of 2.06 mg/dL, R ² = 0.99, and Accuracy of 98.65 % for glucose. The system performance is then evaluated with Bland Altman analysis and Clarke Error Grid Analysis (CEGA).

中文翻译：

---

基于反向传播神经网络的机器学习模型用于预测 CKD 患者的血尿素和血糖

糖尿病及其并发症如心脏病、中风、肾衰竭等是全世界都严重关注的问题。因此，非侵入性且高精度地监测一些重要的血液参数至关重要。本文提出了一种内部开发的系统，该系统将有助于患有慢性肾病（CKD）的糖尿病患者监测血尿素和血糖。本手稿讨论了使用反向传播人工神经网络（BP-ANN）和偏最小二乘回归（PLSR）模型预测血尿素和血糖的比较研究。NVIDIA Jetson Nano 板控制近红外 (NIR) 区域中的五个固定 LED 波长 $2.0~\mu \text{m}$到 $2.5~\mu \text{m}$恒定发射功率为 1.2 mW。记录了 57 个实验室制备的符合血液样本主要血液成分的样本的光谱。从这些样本中，53 个光谱用于 BP-ANN/PLSR 模型的训练/校准，其余 4 个样本用于验证模型。PLSR 模型预测血尿素和血糖的均方根误差 (RMSE) 分别为 0.88 和 12.01 mg/dL，决定系数 R ² = 0.93 和 R ² = 0.97，准确度分别为 94.2 % 和 90.14 %。为了提高预测精度，采用BP-ANN模型。随后，主成分分析 (PCA) 技术被应用于这 57 个光谱值。这些 PCA 值用于训练和验证 BP-ANN 模型。应用BP-ANN模型后，血尿素和血糖的预测显着改善，RMSE为0.69 mg/dL，R ² = 0.96，尿素准确度为95.96 %，RMSE为2.06 mg/dL，R ² = 0.99 ，葡萄糖的准确度为 98.65%。然后使用 Bland Altman 分析和 Clarke 误差网格分析 (CEGA) 评估系统性能。