# Discussion of Cuffless Blood Pressure Prediction Using Plethysmograph Based on a Longitudinal Experiment: Is the Individual Model Necessary?

^{1}

^{2}

^{3}

^{4}

^{5}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Materials and Methods

#### 2.1. Preprocessing

- PPG intensive ratio (PIR): $PIR=PP{G}_{peak}/PP{G}_{root}$, which is an index to reflect changes in the arterial diameter [21];
- Diastole time ratio (DTR): $DTR={t}_{sys}/T$, where the ${t}_{sys}$ is the time from the systole peak to the end of a PPG waveform, and T is the time length of the corresponding PPG waveform;
- ri: $ri=PP{G}_{peak}/PP{G}_{inf}$, where the $PP{G}_{inf}$ is the inflection point of the PPG waveform between the dicrotic notch and the diastolic peak. This parameter is introduced given the disappearance of the diastolic peak, while the inflection point can be found. Given the fact that the PPG amplitudes of inflection point and the diastolic peak are similar, the ri is used as the alternative of the Reflection index [22];
- A02: Area of the 0–2 Hz band of the PPG waveform [6];
- A25: Area of the 2–5 Hz band of the PPG waveform [6].

#### 2.2. Regression Models

#### 2.2.1. Partial Least Squares (PLS)

#### 2.2.2. LW-PLS

#### 2.2.3. Gaussian Process Regression

#### 2.3. Calibration Schemes

#### 2.4. Generalized and Individual Models

## 3. Results

#### 3.1. Results of Generalized Models

**Methods**). By summarizing the regression results of the testing samples, the mean absolute error (MAE) of systolic and diastolic BP is shown in Figure 2, from which it can be seen that none of the models can fit the personal well with MAE larger than 9 mmHg. Therefore, no further comparison of features was conducted for the generalized models.

#### 3.2. Comparison of Different Individual Models

**Methods**section, two calibration schemes were used. The left column corresponds to the calibration using the initial 20% samples (scheme_1), while the right column corresponds to the situation of re-calibrating every 20 samples (scheme_2).

#### 3.3. Regression Model

- SBP: −2.2 ± 6.2 mmHg; DBP: −2.0 ± 5.4 mmHg.

## 4. Discussion

## 5. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Chen, W.; Kobayashi, T.; Ichikawa, S.; Takeuchi, Y.; Togawa, T. Continuous Estimation of Systolic Blood Pressure Using the Pulse Arrival Time and Intermittent Calibration. Med. Biol. Eng. Comput.
**2000**, 38, 569–574. [Google Scholar] [CrossRef] [PubMed] - Tang, Z.; Tamura, T.; Sekine, M.; Huang, M.; Chen, W.; Yoshida, M.; Sakatani, K.; Kobayashi, H.; Kanaya, S. A Chair–Based Unobtrusive Cuffless Blood Pressure Monitoring System Based on Pulse Arrival Time. IEEE J. Biomed. Health Inform.
**2017**, 21, 1194–1205. [Google Scholar] [CrossRef] [PubMed] - Xing, X.; Ma, Z.; Zhang, M.; Zhou, Y.; Dong, W.; Song, M. An Unobtrusive and Calibration-Free Blood Pressure Estimation Method Using Photoplethysmography and Biometrics. Sci. Rep.
**2019**, 9, 1–8. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Shin, H.; Min, S.D. Feasibility study for the non-invasive blood pressure estimation based on PPG morphology: Normotensive subject study. Biomed. Eng. Online
**2017**, 161, 1–14. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Chandrasekhar, A.; Kim, C.S.; Naji, M.; Natarajan, K.; Hahn, J.O.; Mukkamala, R. Smartphone-Based Blood Pressure Monitoring via the Oscillometric Finger-Pressing Method. Sci. Transl. Med.
**2018**, 10, 1–12. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Chowdhury, M.H.; Shuzan, M.N.I.; Chowdhury, M.E.; Mahbub, Z.B.; Uddin, M.M.; Khandakar, A.; Reaz, M.B.I. Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques. Sensors
**2020**, 20, 3127. [Google Scholar] [CrossRef] [PubMed] - Luo, H.; Yang, D.; Barszczyk, A.; Vempala, N.; Wei, J.; Wu, S.J.; Zheng, P.P.; Fu, G.; Lee, K.; Feng, Z.P. Smartphone-based blood pressure measurement using transdermal optical imaging technology. Circ. Cardiovasc. Imaging
**2019**, 128, 1–10. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Foo, J.Y.A.; Lim, C.S.; Wang, P. Evaluation of Blood Pressure Changes Using Vascular Transit Time. Physiol. Meas.
**2006**, 27, 685–694. [Google Scholar] [CrossRef] - Elgendi, M.; Fletcher, R.; Liang, Y.; Howard, N.; Lovell, N.H.; Abbott, D.; Lim, K.; Ward, R. The Use of Photoplethysmography for Assessing Hypertension. Npj Digit. Med.
**2019**, 2, 1–11. [Google Scholar] [CrossRef] [Green Version] - Maeda, Y.; Sekine, M.; Tamura, T. The advantages of wearable green reflected photoplethysmography. J. Med. Syst.
**2011**, 355, 829–834. [Google Scholar] [CrossRef] [PubMed] - Allen, J. Photoplethysmography and its application in clinical physiological measurement. Physiol. Meas.
**2007**, 283, 1–39. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Wisely, N.A.; Cook, L.B. Arterial flow waveforms from pulse oximetry compared with measured Doppler flow waveforms. Anaesthesia
**2001**, 566, 556–561. [Google Scholar] [CrossRef] [PubMed] - O’Rourke, M.F. Vascular impedance in studies of arterial and cardiac function. Physiol. Rev.
**1982**, 622, 570–623. [Google Scholar] [CrossRef] [PubMed] - Allen, J.; Murray, A. Age-related changes in the characteristics of the photoplethysmographic pulse shape at various body sites. Physiol. Meas.
**2003**, 242, 297–307. [Google Scholar] [CrossRef] [PubMed] - Makino, M.; Hayashi, H.; Takezawa, H.; Hirai, M.; Saito, H.; Ebihara, S. Circadian Rhythms of Cardiovascular Functions Are Modulated by the Baroreflex and the Autonomic Nervous System in the Rat. Circulation
**1997**, 96, 1667–1674. [Google Scholar] [CrossRef] - Chen, Y.; Shi, S.; Liu, Y.K.; Huang, S.L.; Ma, T. Cuffless Blood-Pressure Estimation Method Using a Heart-Rate Variability-Derived Parameter. Physiol. Meas.
**2018**, 39, 95002. [Google Scholar] [CrossRef] - Esmaili, A.; Kachuee, M.; Shabany, M. Nonlinear Cuffless Blood Pressure Estimation of Healthy Subjects Using Pulse Transit Time and Arrival Time. IEEE Trans. Instrum. Meas.
**2017**, 66, 3299–3308. [Google Scholar] [CrossRef] [Green Version] - Miki, K.; Yoshimoto, M. Exercise-Induced Modulation of Baroreflex Control of Sympathetic Nerve Activity. Front. Neurosci.
**2018**, 12, 1–6. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Kario, K.; Saito, K.; Sato, K.; Hamasaki, H.; Suwa, H.; Okura, A.; Hoshide, S. Validation of the A&D BP UA-1200BLE device for home blood pressure measurement according to the ISO 81060–2: 2013 standard. Blood Press. Monit.
**2018**, 23, 312–314. [Google Scholar] - Liang, Y.; Elgendi, M.; Chen, Z.; Ward, R. Analysis: An Optimal Filter for Short Photoplethysmogram Signals. Sci. Data
**2018**, 5, 1–12. [Google Scholar] [CrossRef] [PubMed] - Ding, X.; Zhang, Y.; Liu, J.; Dai, W.; Tsang, H.K. Continuous Cuffless Blood Pressure Estimation Using Pulse Transit Time and Photoplethysmogram Intensity Ratio. IEEE Trans. Biomed. Eng.
**2016**, 635, 964–972. [Google Scholar] [CrossRef] [PubMed] - Yousef, Q.; Reaz, M.B.I.; Ali, M.A.M. The Analysis of PPG Morphology: Investigating the Effects of Aging on Arterial Compliance. Meas. Sci. Rev.
**2012**, 12, 266–271. [Google Scholar] [CrossRef] [Green Version] - Hayase, T. Blood Pressure Estimation Based on Pulse Rate Variation in a Certain Period. Sci. Rep.
**2020**, 10, 1–14. [Google Scholar] [CrossRef] - Kollias, A.; Kyriakoulis, K.G.; Stambolliu, E.; Ntineri, A.; Anagnostopoulos, I.; Stergiou, G.S. Seasonal blood pressure variation assessed by different measurement methods: Systematic review and meta-analysis. J. Hypertens.
**2020**, 28, 791–798. [Google Scholar] [CrossRef] [PubMed] - Modesti, P.A.; Morabito, M.; Massetti, L.; Rapi, S.; Orlandini, S.; Mancia, G.; Gensini, G.F.; Parati, G. Seasonal blood pressure changes: An independent relationship with temperature and daylight hours. Hypertension
**2013**, 61, 908–914. [Google Scholar] [CrossRef] [Green Version] - Slapničar, G.; Mlakar, N.; Luštrek, M. Blood Pressure Estimation from Photoplethysmogram Using a Spectro-Temporal Deep Neural Network. Sensors
**2019**, 19, 3420. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Lee, D.; Kwon, H.; Son, D.; Eom, H.; Park, C.; Lim, Y.; Seo, C.; Park, K. Beat-to-beat continuous blood pressure estimation using bidirectional long short-term memory network. Sensors
**2021**, 21, 96. [Google Scholar] [CrossRef]

**Figure 1.**Illustration of PPG features. Inflection point of the PPG waveform between the dicrotic notch and the diastolic peak is used given that the disappearance of the diastolic peak may appear.

**Figure 2.**The mean absolute error (MAE) of systolic and diastolic BP of the three generalized models. The bar plot on the left corresponds to the results with scheme_1 and the bar plot on the right to the results with scheme_2. Sticks show the standard errors.

**Figure 3.**Comparison of three individual models using scheme_1 (left column) and scheme_2 (right column). Sticks show the standard errors.The setx means the combination of PPG features, where the set1 is {hr, a02, a25, ri}, set2 is {pir, dtr, hr, a02, a25, ri}, set3 is {hr, ri}. * means the p < 0.05 and, ** means the p < 0.001. setx_h corresponds to the scheme_1 calibration.

**Figure 4.**The results of the GPR_set1 (scheme_2) model. The fitting of the one-month samples of two randomly selected subjects can be seen in (

**a**,

**b**). The BA plot for and linear correlation can be found in (

**c**,

**d**).

**Figure 5.**Distribution of predicting errors of the PLS_set1 (

**left**column) adn GPR_set1 models (

**right**column). Red curves show the approximation of probability density using Gaussian distribution.

**Figure 6.**Distribution of similarity. Each subfigure corresponds to one subject. In each subfigure, the histogram in red shows the distribution of similarity of samples from the same subject; whereas the one in blue shows the distribution of similarity with other subjects.

Sub. | Ag | Gender | Ref. BP Range | MAE | RMSE | |||
---|---|---|---|---|---|---|---|---|

No. | Yrs. | F/M | SBP | DBP | SBP | DBP | SBP | DBP |

1 | 45 | F | 119–90 | 87–63 | 5.01 | 6.13 | 6.29 | 7.23 |

2 | 43 | M | 131–100 | 98–66 | 4.60 | 4.60 | 5.70 | 5.91 |

3 | 27 | M | 141–101 | 88–65 | 6.23 | 4.60 | 7.62 | 5.57 |

4 | 50 | M | 173–129 | 125–97 | 6.20 | 4.31 | 7.84 | 5.34 |

5 | 46 | F | 110–92 | 79–61 | 3.36 | 4.01 | 4.28 | 4.13 |

6 | 50 | M | 127–94 | 89–69 | 5.63 | 6.83 | 7.30 | 8.95 |

7 | 44 | M | 138–108 | 110–78 | 5.23 | 4.64 | 6.43 | 5.49 |

8 | 25 | F | 119–93 | 81–56 | 4.49 | 3.92 | 5.53 | 4.98 |

9 | 46 | M | 136–91 | 99–72 | 5.70 | 5.37 | 7.77 | 6.84 |

10 | 47 | F | 141–111 | 97–78 | 4.30 | 3.35 | 5.14 | 4.16 |

11 | 29 | F | 144–88 | 93–56 | 6.22 | 4.06 | 8.24 | 4.78 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 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 (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Kido, K.; Chen, Z.; Huang, M.; Tamura, T.; Chen, W.; Ono, N.; Takeuchi, M.; Altaf-Ul-Amin, M.; Kanaya, S.
Discussion of Cuffless Blood Pressure Prediction Using Plethysmograph Based on a Longitudinal Experiment: Is the Individual Model Necessary? *Life* **2022**, *12*, 11.
https://doi.org/10.3390/life12010011

**AMA Style**

Kido K, Chen Z, Huang M, Tamura T, Chen W, Ono N, Takeuchi M, Altaf-Ul-Amin M, Kanaya S.
Discussion of Cuffless Blood Pressure Prediction Using Plethysmograph Based on a Longitudinal Experiment: Is the Individual Model Necessary? *Life*. 2022; 12(1):11.
https://doi.org/10.3390/life12010011

**Chicago/Turabian Style**

Kido, Koshiro, Zheng Chen, Ming Huang, Toshiyo Tamura, Wei Chen, Naoaki Ono, Masachika Takeuchi, Md. Altaf-Ul-Amin, and Shigehiko Kanaya.
2022. "Discussion of Cuffless Blood Pressure Prediction Using Plethysmograph Based on a Longitudinal Experiment: Is the Individual Model Necessary?" *Life* 12, no. 1: 11.
https://doi.org/10.3390/life12010011