A Non-Invasive Continuous Blood Pressure Estimation Approach Based on Machine Learning

Considering the existing issues of traditional blood pressure (BP) measurement methods and non-invasive continuous BP measurement techniques, this study aims to establish the systolic BP and diastolic BP estimation models based on machine learning using pulse transit time and characteristics of pulse waveform. In the process of model construction, the mean impact value method was introduced to investigate the impact of each feature on the models and the genetic algorithm was introduced to implement parameter optimization. The experimental results showed that the proposed models could effectively describe the nonlinear relationship between the features and BP and had higher accuracy than the traditional methods with the error of 3.27 ± 5.52 mmHg for systolic BP and 1.16 ± 1.97 mmHg for diastolic BP. Moreover, the estimation errors met the requirements of the Advancement of Medical Instrumentation and British Hypertension Society criteria. In conclusion, this study was helpful in promoting the practical application of methods for non-invasive continuous BP estimation models.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  Joon-Hyuk Chang,et al.  Oscillometric Blood Pressure Estimation Based on Deep Learning , 2017, IEEE Transactions on Industrial Informatics.

[3]  Ming Liu,et al.  Novel wavelet neural network algorithm for continuous and noninvasive dynamic estimation of blood pressure from photoplethysmography , 2016, Science China Information Sciences.

[4]  Matjaz Gams,et al.  Non-Invasive Blood Pressure Estimation from ECG Using Machine Learning Techniques , 2018, Sensors.

[5]  Huihui Li,et al.  Beat-to-beat ambulatory blood pressure estimation based on random forest , 2016, 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[6]  Xuejun Jiao,et al.  [Research on continuous measurement of blood pressure via characteristic parameters of pulse wave]. , 2002, Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi.

[7]  Hudson Fernandes Golino,et al.  Predicting Increased Blood Pressure Using Machine Learning , 2014, Journal of obesity.

[8]  R. Payne,et al.  Pulse transit time measured from the ECG: an unreliable marker of beat-to-beat blood pressure. , 2006, Journal of applied physiology.

[9]  Mahdi Shabany,et al.  Cuffless Blood Pressure Estimation Algorithms for Continuous Health-Care Monitoring , 2017, IEEE Transactions on Biomedical Engineering.

[10]  Zhuangzhi Yan,et al.  [A noninvasive and continuous method for blood pressure measurement using pulse wave]. , 2011, Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation.

[11]  Yuan-Ting Zhang,et al.  Continuous Cuffless Blood Pressure Estimation Using Pulse Transit Time and Photoplethysmogram Intensity Ratio , 2016, IEEE Transactions on Biomedical Engineering.

[12]  A. Khera,et al.  Target Organ Complications and Cardiovascular Events Associated With Masked Hypertension and White-Coat Hypertension: Analysis From the Dallas Heart Study. , 2015, Journal of the American College of Cardiology.

[13]  George B. Moody,et al.  An Open-source Toolbox for Analysing and Processing PhysioNet Databases in MATLAB and Octave , 2014, Journal of open research software.

[14]  Harald Herkner,et al.  Factors influencing the accuracy of oscillometric blood pressure measurement in critically ill patients , 2003, Critical care medicine.

[15]  Jiadong Ren,et al.  Health Data Driven on Continuous Blood Pressure Prediction Based on Gradient Boosting Decision Tree Algorithm , 2019, IEEE Access.

[16]  M. Irigoyen,et al.  Hypertension, Blood Pressure Variability, and Target Organ Lesion , 2016, Current Hypertension Reports.

[17]  Mingshan Sun,et al.  Optical blood pressure estimation with photoplethysmography and FFT-based neural networks. , 2016, Biomedical optics express.

[18]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[19]  N. Gravenstein,et al.  An Accuracy Evaluation of the T-Line® Tensymeter (Continuous Noninvasive Blood Pressure Management Device) versus Conventional Invasive Radial Artery Monitoring in Surgical Patients , 2006, Anesthesia and analgesia.

[20]  K Affeld,et al.  Continuous Wrist Blood Pressure Measurement with Ultrasound , 2013, Biomedizinische Technik. Biomedical engineering.

[21]  Joon-Hyuk Chang,et al.  Improved Gaussian Mixture Regression Based on Pseudo Feature Generation Using Bootstrap in Blood Pressure Estimation , 2016, IEEE Transactions on Industrial Informatics.

[22]  Guanglin Li,et al.  New photoplethysmogram indicators for improving cuffless and continuous blood pressure estimation accuracy , 2018, Physiological measurement.

[23]  Yadan Zhang,et al.  Non-invasive continuous blood pressure measurement based on mean impact value method, BP neural network, and genetic algorithm , 2018, Technology and health care : official journal of the European Society for Engineering and Medicine.