Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Rugjer Boshkovikj 16, 1000 Skopje, Macedonia.
Department of Intelligent Systems, Jožef Stefan Institute, Jožef Stefan International Postgraduate School, Jamova cesta 39, 1000 Ljubljana, Slovenia.
Sensors (Basel). 2018 Apr 11;18(4):1160. doi: 10.3390/s18041160.
Blood pressure (BP) measurements have been used widely in clinical and private environments. Recently, the use of ECG monitors has proliferated; however, they are not enabled with BP estimation. We have developed a method for BP estimation using only electrocardiogram (ECG) signals.
Raw ECG data are filtered and segmented, and, following this, a complexity analysis is performed for feature extraction. Then, a machine-learning method is applied, combining a stacking-based classification module and a regression module for building systolic BP (SBP), diastolic BP (DBP), and mean arterial pressure (MAP) predictive models. In addition, the method allows a probability distribution-based calibration to adapt the models to a particular user.
Using ECG recordings from 51 different subjects, 3129 30-s ECG segments are constructed, and seven features are extracted. Using a train-validation-test evaluation, the method achieves a mean absolute error (MAE) of 8.64 mmHg for SBP, 18.20 mmHg for DBP, and 13.52 mmHg for the MAP prediction. When models are calibrated, the MAE decreases to 7.72 mmHg for SBP, 9.45 mmHg for DBP and 8.13 mmHg for MAP.
The experimental results indicate that, when a probability distribution-based calibration is used, the proposed method can achieve results close to those of a certified medical device for BP estimation.
血压（BP）测量已广泛应用于临床和私人环境中。最近，心电图监测器的使用也激增，但它们不具备血压估计功能。我们已经开发出一种仅使用心电图（ECG）信号进行血压估计的方法。
原始 ECG 数据经过滤波和分段，然后进行复杂度分析以进行特征提取。然后，应用机器学习方法，结合基于堆叠的分类模块和回归模块，构建收缩压（SBP）、舒张压（DBP）和平均动脉压（MAP）预测模型。此外，该方法允许基于概率分布的校准，以适应特定用户的模型。
使用来自 51 位不同受试者的心电图记录，构建了 3129 个 30 秒 ECG 段，并提取了七个特征。使用训练-验证-测试评估，该方法对 SBP 的平均绝对误差（MAE）为 8.64mmHg，DBP 的 MAE 为 18.20mmHg，MAP 的 MAE 为 13.52mmHg。当对模型进行校准时，MAE 降低到 SBP 的 7.72mmHg、DBP 的 9.45mmHg 和 MAP 的 8.13mmHg。
实验结果表明，当使用基于概率分布的校准时，所提出的方法可以达到与经过认证的血压估计医疗设备相当的结果。
