Optimizing the input feature sets and machine learning algorithms for reliable and accurate estimation of continuous, cuffless blood pressure.

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-

Blood Pressure Determination* ; Photoplethysmography*; Humans ; Blood Pressure/physiology ; Reproducibility of Results ; Algorithms ; Machine Learning ; Pulse Wave Analysis

The advent of mobile devices, wearables and digital healthcare has unleashed a demand for accurate, reliable, and non-interventional ways to measure continuous blood pressure (BP). Many consumer products claim to measure BP with a cuffless device, but their lack of accuracy and reliability limit clinical adoption. Here, we demonstrate how multimodal feature datasets, comprising: (i) pulse arrival time (PAT); (ii) pulse wave morphology (PWM), and (iii) demographic data, can be combined with optimized Machine Learning (ML) algorithms to estimate Systolic BP (SBP), Diastolic BP (DBP) and Mean Arterial Pressure (MAP) within a 5 mmHg bias of the gold standard Intra-Arterial BP, well within the acceptable limits of the IEC/ANSI 80601-2-30 (2018) standard. Furthermore, DBP's calculated using 126 datasets collected from 31 hemodynamically compromised patients had a standard deviation within 8 mmHg, while SBP's and MAP's exceeded these limits. Using ANOVA and Levene's test for error means and standard deviations, we found significant differences in the various ML algorithms but found no significant differences amongst the multimodal feature datasets. Optimized ML algorithms and key multimodal features obtained from larger real-world data (RWD) sets could enable more reliable and accurate estimation of continuous BP in cuffless devices, accelerating wider clinical adoption.
(© 2023. The Author(s).)

Sci Rep. 2021 Jun 29;11(1):13539. (PMID: 34188132)
IEEE Trans Biomed Eng. 2015 Aug;62(8):1879-901. (PMID: 26057530)
Circulation. 2000 Jun 13;101(23):E215-20. (PMID: 10851218)
Crit Care Explor. 2020 Apr 29;2(4):e0095. (PMID: 32426737)
J Hypertens. 1992 May;10(5):401-9. (PMID: 1317899)
Hypertension. 2023 Mar;80(3):534-540. (PMID: 36458550)
Front Cardiovasc Med. 2019 Apr 30;6:40. (PMID: 31157236)
J Clin Monit. 1995 Jul;11(4):245-52. (PMID: 7561998)
Cardiol Clin. 2002 May;20(2):207-23. (PMID: 12119797)
Sci Rep. 2021 Nov 23;11(1):22767. (PMID: 34815419)
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:6838-6841. (PMID: 31947411)
Physiol Meas. 2019 Jul 23;40(7):075001. (PMID: 31051486)
IEEE Trans Biomed Eng. 2013 Jul;60(7):1814-24. (PMID: 23372068)
Expert Syst Appl. 2022 Nov 30;207:118029. (PMID: 35812003)
IEEE J Biomed Health Inform. 2022 Jul;26(7):2864-2875. (PMID: 35201992)
Physiol Meas. 2018 Sep 24;39(9):095005. (PMID: 30109991)
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:7060-7063. (PMID: 31947463)
Hypertension. 2002 May;39(5):963-8. (PMID: 12019277)
J Hypertens. 2022 Aug 1;40(8):1449-1460. (PMID: 35708294)
Intensive Care Med. 2013 Sep;39(9):1618-25. (PMID: 23740275)
Hypertension. 2011 Jan;57(1):29-38. (PMID: 21115879)
Proc ACM Interact Mob Wearable Ubiquitous Technol. 2017 Sep;1(3):. (PMID: 30556049)
Comput Biol Med. 2023 Jan;152:106457. (PMID: 36571937)
Front Physiol. 2019 Sep 12;10:1179. (PMID: 31572224)
J Clin Monit. 1995 Sep;11(5):324-8. (PMID: 7595689)
Sci Rep. 2021 Dec 10;11(1):23809. (PMID: 34893674)
Circ J. 2006 Oct;70(10):1231-9. (PMID: 16998252)
Sensors (Basel). 2011;11(2):1784-93. (PMID: 22319381)
J Hypertens. 2002 Apr;20(4):629-38. (PMID: 11910297)
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:4673-4676. (PMID: 31946905)

Date Created: 20230512 Date Completed: 20230515 Latest Revision: 20230606

20231215

PMC10181996

10.1038/s41598-023-34677-9

37173370