# Advanced Bio-Inspired System for Noninvasive Cuff-Less Blood Pressure Estimation from Physiological Signal Analysis

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Related Works

- classical analytic methods;
- Pulse Transit Time (PTT)-based methods, involving both ElectroCardioGraphy (ECG) and PPG signals;
- heuristic approaches based on key features of PPG standard waveforms;
- (artificial) neural networks/machine learning algorithms;
- mixed ECG-PPG approaches.

- knowledge of specific physical parameters (arterial vessel elasticity, Moens–Korteweg equation, etc.);
- the related systems, both HW (Hardware) and SW (Software) (PPG/ECG) sensors, data extraction (PTT, PWV), etc., may turn out to be unduly complex;
- a sensitivity/specificity ratio hardly compatible with the related (high) computational costs;
- continuous ECG acquisition may be mandatory, with relates the difficulties of detection in certain contexts such as the automotive sector or smartphone systems;
- those methods that are based on machine learning and (Artificial) Neural Networks (ANNs) may involve high computational costs against a reduced accuracy and/or a high estimation capability limited to a reduced pressure range (80–90/110–130 mmHg);

## 3. The Photoplethysmography System (BI-P${}^{\mathbf{2}}$RS): A Brief Overview

- a Systolic Peak (SP),
- a Dicrotic Notch (DN),
- a Diastolic Peak (DP) at a value y,
- the Width (W) of the pulse waveform.

## 4. The Proposed Blood Pressure Estimation System

**ln**denotes the (natural) logarithm;**N${}_{PPG}$**: the number of compliant PPG waveforms over a period of the analyzed PPG signal;- the suffixes
**sys**,**dia**and**dic**denote the systolic, diastolic and dicrotic phases of the PPG signal (see, e.g., Figure 1), which may be identified as the portions a–b, a1–b1, a2–b2 (systolic), b–d, b1–d1, b2–d2 (dicrotic), c–e, c1-e1 and c2–e2 (diastolic) in the diagrams (PPG and its first derivative and second derivative) of Figure 5; - L${}^{i}$x indicates the length of the sub-curve of the PPG waveform, for the systolic, diastolic and dicrotic phases sys, dia and dic, respectively, and with $i=1$,
**N${}_{PPG}$**; in the same way, L${}^{i}$x (∂PPG/∂t) represents the length of the sub-curve of the first derivative of the PPG signal, and L${}^{i}$x (∂${}^{2}$PPG/∂t${}^{2}$) represents the length of the sub-curve of the second derivative of the PPG signal, again for sys, dia and dic, respectively. For the first derivative and second derivative of PPG signal, the Simpson rule can be adopted for computing the length of the curve [28]; - σ${}_{x}$ the denotes standard deviation for variable L${}^{i}$x.

- max denotes the point (abscissa) where the PPG waveform has its maximum value (systolic peak SP);
- min denotes the point (abscissa) where the PPG waveform has its minimum value;
- p${}^{i}$ denotes the dicrotic point (abscissa);
- i and ($i+1$) generally denote two subsequent PPG waveforms.

## 5. Testing and Future Works

## Author Contributions

## Funding

## Conflicts of Interest

## References

- McCombie, D.B.; Andrew, T.R.; Asada, H.H. Adaptive blood pressure estimation from wearable PPG sensors using peripheral artery pulse wave velocity measurements and multi-channel blind identification of local arterial dynamics. In Proceedings of the 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, New York, NY, USA, 30 August–3 Septenber 2006; pp. 3521–3524. [Google Scholar]
- Nichols, W.; O’Rourke, M.F. McDonald’s Blood Flow in Arteries: Theoretical, Experimental and Clinical Principles, 4th ed.; CRC Press: London, UK, 1998. [Google Scholar]
- Tijsseling, A.S.; Anderson, A.A. Isebree Moens and D.J. Korteweg: On the speed of propagation of waves in elastic tubes. BHR Group. In Proceedings of the 11th International Conference on Pressure Surges, Lisbon, Portugal, 24–26 October 2012; Anderson, S., Ed.; pp. 227–245, ISBN 978-1-85598-133-1. [Google Scholar]
- Kurylyak, Y.; Lamonaca, F.; Grimaldi, D. A Neural Network-based method for continuous blood pressure estimation from a PPG signal. In Proceedings of the IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Torino, Italy, 22–25 May 2013; pp. 280–283. [Google Scholar]
- Yan, Y.S.; Zhang, Y.T. Noninvasive estimation of blood pressure using photoplethysmographic signals in the period domain. In Proceedings of the 27th Annual International Conference of the Engineering in Medicine and Biology Society (IEEE-EMBS 2005), Shanghai, China, 1–4 September 2005; pp. 3583–3584. [Google Scholar]
- Gu, W.B.; Poon, C.C.Y.; Zhang, Y.T. A novel parameter from PPG dicrotic notch for estimation of systolic blood pressure using pulse transit time. In Proceedings of the 5th International Summer School and Symposium on Medical Devices and Biosensors (ISSS-MDBS 2008), Hong Kong, China, 1–3 June 2008; pp. 86–88. [Google Scholar]
- Meigas, K.; Kattai, R.; Lass, J. Continuous blood pressure monitoring using pulse wave delay. In Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Istanbul, Turkey, 25–28 October 2001; pp. 3171–3174. [Google Scholar] [Green Version]
- Cattivelli, F.S.; Garudadri, H. Noninvasive cuffless estimation of blood pressure from pulse arrival time and heart rate with adaptive calibration. In Proceedings of the Sixth International Workshop on Wearable and Implantable Body Sensor Networks (BSN 2009), Berkeley, CA, USA, 3–5 June 2009; pp. 114–119. [Google Scholar]
- Teng, X.F.; Zhang, Y.T. Continuous and noninvasive estimation of arterial blood pressure using a photoplethysmographic approach. In Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Cancun, Mexico, 17–21 September 2003; pp. 3153–3156. [Google Scholar]
- Fortino, G.; Giampà, V. PPG-based methods for non invasive and continuous BP measurement: an overview and development issues in body sensor networks. In Proceedings of the IEEE International Workshop on Medical Measurements and Applications (MeMeA’2010), Ottawa, ON, Canada, 30 April–1 May 2010; pp. 10–13. [Google Scholar]
- Kim, J.Y.; Cho, B.H.; Im, S.M.; Jeon, M.J.; Kim, I.Y.; Kim, S.I. Comparative study on artificial neural network with multiple regressions for continuous estimation of blood pressure. In Proceedings of the 27th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Shanghai, China, 1–4 September 2005; pp. 6942–6945. [Google Scholar]
- Goldberger, A.L.; Amaral, L.A.; Glass, L.; Hausdorff, J.M.; Ivanov, P.C.; Mark, R.G.; Mietus, J.E.; Moody, G.B.; Peng, C.K.; Stanley, H.E. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation
**2000**, 101, 215–220. [Google Scholar] [CrossRef] - Kurylyak, Y.; Lamonaca, F.; Grimaldi, D. Smartphone-Based Photoplethysmogram Measurement. In Digital Image and Signal Processing for Measurement Systems; Duro, R.J., López-Peña, F., Eds.; River Publisher: River City, Denmark, 2012; pp. 135–164. [Google Scholar]
- Lamonaca, F.; Kurylyak, Y.; Grimaldi, D.; Spagnuolo, V. Reliable pulse rate evaluation by smartphone. In Proceedings of the IEEE International Symposium on Medical Measurements and Applications Proceedings (MeMeA 2012), Budapest, Hungary, 18–19 May 2012; pp. 234–237. [Google Scholar]
- Gaurav, A.; Maheedhar, M.; Tiwari, V.N.; Narayanan, R. Cuff-less PPG based continuous blood pressure monitoring—A smartphone based approach. In Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA, 16–20 August 2016; pp. 607–610. [Google Scholar]
- Datta, S.; Banerjee, R.; Choudhury, A.D.; Sinha, A.; Pal, A. Blood pressure estimation from photoplethysmogram using latent parameters. In Proceedings of the 2016 IEEE International Conference on Communications (ICC), Kuala Lumpur, Malaysia, 22–27 May 2016; pp. 1–7. [Google Scholar]
- Kao, Y.H.; Paul, C.-P.C.; Wey, C.-L. A PPG sensor for continuous cuffless blood pressure monitoring with self-adaptive signal processing. In Proceedings of the 2017 International Conference on Applied System Innovation (ICASI), Sapporo, Japan, 13–17 May 2017; pp. 357–360. [Google Scholar]
- Slapničar, G.; Luštrek, M.; Marinko, M. Continuous Blood Pressure Estimation from PPG Signal. Informatica
**2018**, 42, 33–42. [Google Scholar] - Kachuee, M.; Kiani, M.M.; Mohammadzade, H.; Shabany, M. Cuff-less high-accuracy calibration-free blood pressure estimation using pulse transit time. In Proceedings of the 2015 IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, Portugal, 24–27 May 2015; pp. 1006–1009. [Google Scholar]
- Oreggia, D.; Guarino, S.; Parisi, A.; Pernice, R.; Adamo, G.; Mistretta, L.; Di Buono, P.; Fallica, G.; Cino, C.A.; Busacca, A.C. Physiological parameters measurements in a cardiac cycle via a combo PPG-ECG system. In Proceedings of the AEIT International Annual Conference, Naples, Italy, 14–16 October 2015; pp. 1–6. [Google Scholar]
- Vinciguerra, V.; Ambra, E.; Maddiona, L.; Oliveri, S.; Romeo, M.F.; Mazzillo, M.; Rundo, F.; Fallica, G. Progresses towards a Processing Pipeline in Photoplethysmogram (PPG) based on SiPMs. In Proceedings of the 23 European Conference on Circuit Theory and Design, Catania, Italy, 4–6 September 2017. [Google Scholar]
- Tang, S.K.D.; Goh, S.; Wong, M.L.D.; Lew, Y.E. PPG signal reconstruction using a combination of discrete wavelet transform and empirical mode decomposition. In Proceedings of the 6th International Conference on Intelligent and Advanced Systems (ICIAS), Kuala Lumpur, Malaysia, 15–17 August 2016; pp. 1–4. [Google Scholar]
- Yadhuraj, S.R.; Sudarshan, B.G. GUI creation for removal of motion artifact in PPG signals. In Proceedings of the 3rd International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, 22–23 January 2016; pp. 1–5. [Google Scholar]
- Rundo, F.; Conoci, S.; Ortis, A.; Battiato, S. An Advanced Bio-Inspired PhotoPlethysmoGraphy (PPG) and ECG Pattern Recognition System for Medical Assessment. Sensors
**2018**, 18, 405. [Google Scholar] [CrossRef] [PubMed] - Mazzillo, M.; Maddiona, L.; Rundo, F.; Sciuto, A.; Libertino, S.; Lombardo, S.; Fallica, G. Characterization of sipms with nir long-pass interferential and plastic filters. IEEE Photonics J.
**2018**, 10, 1–12. [Google Scholar] [CrossRef] - Mazzillo, M.; Nagy, F.; Sanfilippo, D.; Valvo, G.; Carbone, B.; Piana, A.; Fallica, G. Silicon photomultiplier technology for low-light intensity detection. Sensors
**2013**, 13, 1–4. [Google Scholar] [CrossRef] - Mazzillo, M.; Mello, D.; Barbarino, P.P.; Romeo, M.F.; Musienko, Y.; Sciuto, A.; Libertino, S.; Lombardo, S.A.; Fallica, G. Electro-Optical Characterization of SiPMs With Green Bandpass Dichroic Filters. IEEE Sens. J.
**2017**, 17, 4075–4082. [Google Scholar] [CrossRef] - Matthews, J.H. Simpson’s 3/8 Rule for Numerical Integration. Numerical Analysis-Numerical Methods Project. California State University, Fullerton Archived from the original on 4 December 2008. Retrieved 11 November 2008. Available online: http://mathfaculty.fullerton.edu/mathews/N340/Math340.htm (accessed on 28 August 2018).
- Fletcher, R.; Reeves, C.M. Function minimizazion by conjugate gradients. Comput. J.
**1964**, 7, 149–154. [Google Scholar] [CrossRef] - Hagan, M.T.; Demuth, H.B.; Beale, M.H.; De Jesús, O. Neural Network Design; PWS Publishing: Boston, MA, USA, 1996; pp. 9-15–9-22. [Google Scholar]
- Arena, P.; Bucolo, M.; Fortuna, L.; Frasca, M. Motor map for nonlinear control. In Proceedings of the 6th Experimental Chaos Conference, Potsdam, Germany, 22–26 July 2001. [Google Scholar]
- Battiato, S.; Rundo, F.; Stanco, F. An Improved Image Re-Indexing Technique by Self Organizing Motor Maps. In International Workshop on Computational Color Imaging; Springer: Berlin/Heidelberg, Germany, 2009. [Google Scholar]
- Battiato, S.; Rundo, F.; Stanco, F. Self organizing motor maps for color-mapped image re-indexing. IEEE Trans. Image Process.
**2007**, 16, 2905–2915. [Google Scholar] [CrossRef] [PubMed]

**Figure 1.**A compliant standard PPG waveform. The different signal components are detailed: Systolic Peak (SP), Dicrotic Notch (DN) and Diastolic Peak (DP).

**Figure 3.**Detailed description of the whole PPG signal sampling system and pattern recognition pipeline. PTT, Pulse Transmit Time.

**Figure 4.**Detailed description of the proposed blood pressure estimation algorithm. BI-P2RS, Bio-Inspired PPG Pattern Recognition System.

**Figure 6.**Detailed description of the variables used for hand-crafted features F${}_{37}$–F${}_{42}$.

**Figure 8.**Performance diagrams of the Polak–Ribiere neural network over nine epochs (blue: learning/green: validation).

**Figure 9.**SOM motor map input layer winner neuron distribution (red neurons) during the learning process.

$F}_{1}=\mathrm{ln}\left(\right)open="("\; close=")">\frac{1}{{N}_{PPG}}\left(\right)open="("\; close=")">\sum _{i=1}^{{N}_{PPG}}{L}_{sys}^{i$ | ${F}_{2}=\mathrm{ln}\left(\right)open="("\; close=")">\frac{1}{{N}_{PPG}}\left(\right)open="("\; close=")">\sum _{i=1}^{{N}_{PPG}}{L}_{sys}^{i}(\frac{\partial PPG}{\partial t})$ | ${F}_{3}=\mathrm{ln}\left(\right)open="("\; close=")">\frac{1}{{N}_{PPG}}\left(\right)open="("\; close=")">\sum _{i=1}^{{N}_{PPG}}{L}_{sys}^{i}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}})$ |

$F}_{4}={\sigma}_{{L}_{sys}$ | ${F}_{5}={\sigma}_{{L}_{sys}}(\frac{\partial PPG}{\partial t})$ | ${F}_{6}={\sigma}_{{L}_{sys}}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}})$ |

$F}_{7}=\mathrm{ln}\left(\right)open="("\; close=")">\frac{1}{{N}_{PPG}}\left(\right)open="("\; close=")">\sum _{i=1}^{{N}_{PPG}}{L}_{dia}^{i$ | ${F}_{8}=\mathrm{ln}\left(\right)open="("\; close=")">\frac{1}{{N}_{PPG}}\left(\right)open="("\; close=")">\sum _{i=1}^{{N}_{PPG}}{L}_{dia}^{i}(\frac{\partial PPG}{\partial t})$ | ${F}_{9}=\mathrm{ln}\left(\right)open="("\; close=")">\frac{1}{{N}_{PPG}}\left(\right)open="("\; close=")">\sum _{i=1}^{{N}_{PPG}}{L}_{dia}^{i}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}})$ |

$F}_{10}={\sigma}_{{L}_{dia}$ | ${F}_{11}={\sigma}_{{L}_{dia}}(\frac{\partial PPG}{\partial t})$ | ${F}_{12}={\sigma}_{{L}_{dia}}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}})$ |

$F}_{13}=\mathrm{ln}\left(\right)open="("\; close=")">\frac{1}{{N}_{PPG}}\left(\right)open="("\; close=")">\sum _{i=1}^{{N}_{PPG}}{L}_{dic}^{i$ | ${F}_{14}=\mathrm{ln}\left(\right)open="("\; close=")">\frac{1}{{N}_{PPG}}\left(\right)open="("\; close=")">\sum _{i=1}^{{N}_{PPG}}{L}_{dic}^{i}(\frac{\partial PPG}{\partial t})$ | ${F}_{15}=\mathrm{ln}\left(\right)open="("\; close=")">\frac{1}{{N}_{PPG}}\left(\right)open="("\; close=")">\sum _{i=1}^{{N}_{PPG}}{L}_{dic}^{i}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}})$ |

$F}_{16}={\sigma}_{{L}_{dic}$ | ${F}_{17}={\sigma}_{{L}_{dic}}(\frac{\partial PPG}{\partial t})$ | ${F}_{18}={\sigma}_{{L}_{dic}}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}})$ |

$F}_{19}=\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}}\frac{{L}_{sys}^{i}}{{L}_{dia}^{i}$ | ${F}_{20}=\sigma (\frac{{L}_{sys}}{{L}_{dia}})$ | ${F}_{21}=\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}}\frac{{L}_{sys}^{i}}{{L}_{dia}^{i}}(\frac{\partial PPG}{\partial t})$ |

${F}_{22}=\sigma (\frac{{L}_{sys}}{{L}_{dia}}(\frac{\partial PPG}{\partial t}))$ | ${F}_{23}=\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}}\frac{{L}_{sys}^{i}}{{L}_{dia}^{i}}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}})$ | ${F}_{24}=\sigma (\frac{{L}_{sys}}{{L}_{dia}}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}}))$ |

$F}_{25}=\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}}\frac{{L}_{sys}^{i}}{{L}_{dic}^{i}$ | ${F}_{26}=\sigma (\frac{{L}_{Sys}}{{L}_{dic}})$ | ${F}_{27}=\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}}\frac{{L}_{sys}^{i}}{{L}_{dic}^{i}}(\frac{\partial PPG}{\partial t})$ |

${F}_{28}=\sigma (\frac{{L}_{sys}}{{L}_{dic}}(\frac{\partial PPG}{\partial t}))$ | ${F}_{29}=\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}}\frac{{L}_{sys}^{i}}{{L}_{dic}^{i}}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}})$ | ${F}_{30}=\sigma (\frac{{L}_{Sys}}{{L}_{dic}}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}}))$ |

$F}_{31}=\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}}\frac{{L}_{dia}^{i}}{{L}_{dic}^{i}$ | ${F}_{32}=\sigma (\frac{{L}_{dia}}{{L}_{dic}})$ | ${F}_{33}=\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}}\frac{{L}_{dia}^{i}}{{L}_{dic}^{i}}(\frac{\partial PPG}{\partial t})$ |

${F}_{34}=\sigma (\frac{{L}_{dia}}{{L}_{dic}}(\frac{\partial PPG}{\partial t}))$ | ${F}_{35}=\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}}\frac{{L}_{dia}^{i}}{{L}_{dic}^{i}}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}})$ | ${F}_{36}=\sigma (\frac{{L}_{dia}}{{L}_{dic}}(\frac{{\partial}^{2}PPG}{\partial {t}^{2}}))$ |

${F}_{37}=\mathrm{ln}(\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}-1}({min}_{dia-PPG}^{i+1}-{min}_{dia-PPG}^{i}))$ | ${F}_{38}=\mathrm{ln}(\sigma ({min}_{dia-PPG}^{i+1}-{min}_{dia-PPG}^{i}))$ |

${F}_{39}=\mathrm{ln}(\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}-1}({max}_{sys-PPG}^{i+1}-{max}_{sys-PPG}^{i}))$ | ${F}_{40}=\mathrm{ln}(\sigma ({max}_{sys-PPG}^{i+1}-{max}_{sys-PPG}^{i}))$ |

${F}_{41}=\mathrm{ln}(\frac{1}{{N}_{PPG}}\sum _{i=1}^{{N}_{PPG}-1}({p}_{dic-PPG}^{i+1}-{p}_{dic-PPG}^{i}))$ | ${F}_{42}=\mathrm{ln}(\sigma ({p}_{dic-PPG}^{i+1}-{p}_{dic-PPG}^{i}))$ |

© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Rundo, F.; Ortis, A.; Battiato, S.; Conoci, S.
Advanced Bio-Inspired System for Noninvasive Cuff-Less Blood Pressure Estimation from Physiological Signal Analysis. *Computation* **2018**, *6*, 46.
https://doi.org/10.3390/computation6030046

**AMA Style**

Rundo F, Ortis A, Battiato S, Conoci S.
Advanced Bio-Inspired System for Noninvasive Cuff-Less Blood Pressure Estimation from Physiological Signal Analysis. *Computation*. 2018; 6(3):46.
https://doi.org/10.3390/computation6030046

**Chicago/Turabian Style**

Rundo, Francesco, Alessandro Ortis, Sebastiano Battiato, and Sabrina Conoci.
2018. "Advanced Bio-Inspired System for Noninvasive Cuff-Less Blood Pressure Estimation from Physiological Signal Analysis" *Computation* 6, no. 3: 46.
https://doi.org/10.3390/computation6030046