Examining the challenges of blood pressure estimation via photoplethysmogram.

Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE

Original Publication: London : Nature Publishing Group, copyright 2011-

Photoplethysmography*/methods ; Blood Pressure*/physiology; Humans ; Pulse Wave Analysis/methods ; Blood Pressure Determination/methods ; Signal Processing, Computer-Assisted ; Deep Learning ; Wearable Electronic Devices

The use of observed wearable sensor data (e.g., photoplethysmograms [PPG]) to infer health measures (e.g., glucose level or blood pressure) is a very active area of research. Such technology can have a significant impact on health screening, chronic disease management and remote monitoring. A common approach is to collect sensor data and corresponding labels from a clinical grade device (e.g., blood pressure cuff) and train deep learning models to map one to the other. Although well intentioned, this approach often ignores a principled analysis of whether the input sensor data have enough information to predict the desired metric. We analyze the task of predicting blood pressure from PPG pulse wave analysis. Our review of the prior work reveals that many papers fall prey to data leakage and unrealistic constraints on the task and preprocessing steps. We propose a set of tools to help determine if the input signal in question (e.g., PPG) is indeed a good predictor of the desired label (e.g., blood pressure). Using our proposed tools, we found that blood pressure prediction using PPG has a high multi-valued mapping factor of 33.2% and low mutual information of 9.8%. In comparison, heart rate prediction using PPG, a well-established task, has a very low multi-valued mapping factor of 0.75% and high mutual information of 87.7%. We argue that these results provide a more realistic representation of the current progress toward the goal of wearable blood pressure measurement via PPG pulse wave analysis. For code, see our project page: https://github.com/lirus7/PPG-BP-Analysis.
(© 2024. The Author(s).)

Circulation. 2000 Jun 13;101(23):E215-20. (PMID: 10851218)
IEEE Trans Biomed Eng. 2012 Feb;59(2):303-6. (PMID: 21803676)
Hypertension. 2020 Feb;75(2):285-292. (PMID: 31865786)
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:607-610. (PMID: 28268403)
Hypertens Res. 2023 Apr;46(4):922-931. (PMID: 36781979)
Circ Res. 2019 Mar 15;124(6):930-937. (PMID: 30646822)
Am J Hypertens. 2014 May;27(5):734-41. (PMID: 24084586)
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:6385-6388. (PMID: 28269709)
Hypertension. 2018 Mar;71(3):368-374. (PMID: 29386350)
Sensors (Basel). 2020 Sep 17;20(18):. (PMID: 32957479)
J Appl Physiol (1985). 1993 May;74(5):2566-73. (PMID: 8335593)
Phys Rev E Stat Nonlin Soft Matter Phys. 2004 Jun;69(6 Pt 2):066138. (PMID: 15244698)
IEEE Trans Biomed Eng. 2015 Aug;62(8):1879-901. (PMID: 26057530)
Healthc Technol Lett. 2019 Nov 26;7(1):7-12. (PMID: 32190335)
Blood Press Monit. 1996 Jun;1(3):181-185. (PMID: 10226223)
NPJ Digit Med. 2021 Jun 2;4(1):89. (PMID: 34079049)
Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:5658-5662. (PMID: 34892406)
Sci Rep. 2021 Aug 3;11(1):15755. (PMID: 34344934)
Sens Int. 2021;2:100117. (PMID: 34806053)
J Am Heart Assoc. 2022 Aug 16;11(16):e026420. (PMID: 35929469)
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:5002-5005. (PMID: 30441464)
IEEE J Biomed Health Inform. 2022 Jul;26(7):2864-2875. (PMID: 35201992)
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:4269-4272. (PMID: 33018939)
NPJ Digit Med. 2019 Jun 26;2:60. (PMID: 31388564)
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:6389-92. (PMID: 21096700)
Annu Rev Biomed Eng. 2022 Jun 6;24:203-230. (PMID: 35363536)
Bioengineering (Basel). 2022 Nov 15;9(11):. (PMID: 36421093)
Opt Express. 2010 May 10;18(10):10762-74. (PMID: 20588929)
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:5042-5045. (PMID: 31946992)
Hypertension. 2021 Nov;78(5):1161-1167. (PMID: 34510915)
IEEE Trans Biomed Eng. 2016 May;63(5):964-972. (PMID: 26415147)
Sensors (Basel). 2020 Oct 04;20(19):. (PMID: 33020401)
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:766-769. (PMID: 28324937)
J Healthc Eng. 2018 Mar 7;2018:7804243. (PMID: 29707186)
Sensors (Basel). 2022 Oct 24;22(21):. (PMID: 36365837)
Sensors (Basel). 2022 Jan 25;22(3):. (PMID: 35161664)
J Hypertens. 2003 May;21(5):821-48. (PMID: 12714851)
Proc Natl Acad Sci U S A. 1959 Aug;45(8):1288-90. (PMID: 16590506)
Sensors (Basel). 2021 Apr 23;21(9):. (PMID: 33922447)
Proc Inst Mech Eng H. 2015 Jul;229(7):499-505. (PMID: 26040284)
Physiol Meas. 2015 Mar;36(3):R1-26. (PMID: 25694235)
Sensors (Basel). 2019 Aug 04;19(15):. (PMID: 31382703)

Date Created: 20240807 Date Completed: 20240807 Latest Revision: 20240812

20240813

PMC11306225

10.1038/s41598-024-68862-1

39112533