Kermani Ali, Esmaeili Hossein
Electrical & Computer Engineering Department, University of Science & Technology of Mazandaran, Behshahr, Iran.
Electrical Department, Shahrood University of Technology, Shahrood, Iran.
Bioimpacts. 2025 Aug 9;15:30589. doi: 10.34172/bi.30589. eCollection 2025.
Accurate and non-invasive blood glucose estimation is essential for effective health monitoring. Traditional methods are invasive and inconvenient, often leading to poor patient compliance. This study introduces a novel approach that leverages systolic-diastolic framing Mel-frequency cepstral coefficients (SDFMFCC) to enhance the accuracy and reliability of blood glucose estimation using photoplethysmography (PPG) signals.
The proposed method employs SDFMFCC for feature extraction, incorporating systolic and diastolic frames. The systolic and diastolic points are identified using the Savitzky-Golay filter, followed by local extrema detection. Blood glucose levels are estimated using support vector regression (SVR). The evaluation is performed on a dataset comprising 67 raw PPG signal samples, along with labeled demographic and biometric data collected from 23 volunteers (aged 20 to 60 years) under informed consent and ethical guidelines.
The SDFMFCC-based approach demonstrates high accuracy (99.8%) and precision (0.996), with a competitive root mean square error (RMSE) of 26.01 mg/dL. The Clarke Error Grid analysis indicates that 99.273% of predictions fall within Zone A, suggesting clinically insignificant differences between estimated and actual glucose levels.
The study validates the hypothesis that incorporating a new framing method in MFCC feature extraction significantly enhances the accuracy and reliability of non-invasive blood glucose estimation. The results highlight that the SDFMFCC method effectively captures critical physiological variations in PPG signals, offering a promising alternative to traditional invasive methods.
准确且无创的血糖估计对于有效的健康监测至关重要。传统方法具有侵入性且不方便，常常导致患者依从性差。本研究引入了一种新颖的方法，该方法利用收缩-舒张帧梅尔频率倒谱系数（SDFMFCC）来提高使用光电容积脉搏波描记术（PPG）信号进行血糖估计的准确性和可靠性。
所提出的方法采用SDFMFCC进行特征提取，纳入了收缩帧和舒张帧。使用Savitzky-Golay滤波器识别收缩点和舒张点，随后进行局部极值检测。使用支持向量回归（SVR）估计血糖水平。在一个包含67个原始PPG信号样本的数据集上进行评估，同时还有在获得知情同意并遵循伦理准则的情况下从23名志愿者（年龄在20至60岁之间）收集的标记人口统计学和生物特征数据。
基于SDFMFCC的方法显示出高精度（99.8%）和高精确度（0.996），具有竞争力的均方根误差（RMSE）为26.01mg/dL。克拉克误差网格分析表明，99.273%的预测落在A区，这表明估计的血糖水平与实际血糖水平之间在临床上差异不显著。
该研究验证了在MFCC特征提取中纳入新的帧方法可显著提高无创血糖估计的准确性和可靠性这一假设。结果突出表明，SDFMFCC方法有效地捕捉了PPG信号中的关键生理变化，为传统侵入性方法提供了一种有前景的替代方案。
