IP Library › Granted Patent US 12,661,070
Granted Patent B2
US 12,661,070 · App. 18/133,434 · Granted Jun 23, 2026

Machine learning techniques for estimating carotid-femoral pulse wave velocity and/or vascular age from single-site arterial waveform measurements

Inventors: Gary F. Mitchell (Dover, MA); John D. Gotal (Framingham, MA)
Assignee: Cardiovascular Engineering, Inc.
A61B5/7264A61B5/02007A61B5/02125G16H50/30
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,661,070
App. No.
18/133,434
Filed
Apr 11, 2023
Granted
Jun 23, 2026
Kind
B2
Art Unit
3791
USPC
600/485
Abstract

Machine learning techniques for estimating an indication of carotid-femoral pulse wave velocity (CFPWV) and/or vascular age (VA) of a subject from an arterial waveform previously measured at a single site by an arterial waveform acquisition device coupled to the subject, the method comprising using at least one computer hardware processor to perform: obtaining the arterial waveform, the arterial waveform comprising a plurality of portions corresponding to a respective plurality of heartbeats of the subject; generating a representative heartbeat waveform from the arterial waveform; and providing the representative heartbeat waveform as input to a trained machine learning model to produce a corresponding output indicative of the CFPWV of the subject.

Claims (60)

1 . A method for using a machine learning model to estimate an indication of carotid-femoral pulse wave velocity (CFPWV) and/or vascular age (VA) of a subject from an arterial waveform previously measured at a single site by an arterial waveform acquisition device coupled to the subject, the method comprising:

using at least one computer hardware processor to perform:

obtaining the arterial waveform, the arterial waveform comprising a plurality of portions corresponding to a respective plurality of heartbeats of the subject, the plurality of portions comprising at least 10 portions, each of the plurality of portions comprising at least 250 data points;

generating a representative heartbeat waveform from the arterial waveform, the generating comprising:

detecting the plurality of portions in the arterial waveform;

individually detrending each of the detected plurality of portions to obtain a plurality of detrended portions,

averaging portions in the plurality of detrended portions to obtain the representative heartbeat waveform; and

processing the representative heartbeat waveform and at least one derivative waveform of the representative heartbeat waveform using a trained one-dimensional (1D) convolutional neural network (CNN) model to produce a corresponding output indicative of the CFPWV of the subject,

wherein the 1D CNN comprises multiple 1D convolutional layers, multiple rectified linear unit layers, multiple pooling layers, and a fully-connected layer,

wherein the 1D CNN comprises at least one million parameters, and

wherein the processing comprises calculating the output indicative of the CFPWV from the representative heartbeat waveform the at least one derivative waveform and the at least one million parameters.

2 . The method of claim 1 , wherein the arterial waveform acquisition device comprises a tonometer, a plethysmographic (PG) device, an echocardiographic device, a digital blood pressure system, an electrical impedance sensor, and/or an ultrasound imaging device.

3 . The method of claim 1 , wherein the arterial waveform acquisition device comprises a wearable device.

4 . The method of claim 1 , wherein the arterial waveform comprises a pressure waveform or an arterial distension waveform.

5 . The method of claim 1 , wherein the arterial waveform comprises an arterial flow waveform.

6 . The method of claim 1 , wherein the plurality of portions comprises at least 100 portions corresponding to a respective plurality of heart beats.

7 . The method of claim 1 , wherein each portion of the plurality of portions comprises at least 500 data points.

8 . The method of claim 1 , further comprising:

removing one or more portions from the detected plurality of portions prior to performing the detrending.

9 . The method of claim 1 , wherein generating the heartbeat waveform from the arterial waveform comprises:

after detecting the plurality of portions in the arterial waveform, removing one or more portions from the detected plurality of portions to obtain a filtered plurality of portions; and

determining a period for the filtered plurality of portions,

wherein the individually detrending is performed on at least some of the filtered plurality of portions and based on the determined period to obtain the plurality of detrended portions.

10 . The method of claim 1 , further comprising:

predicting vascular age (VA) of the subject using a linear regression model different from the trained machine learning model and the output indicative of the CFPWV of the subject.

11 . The method of claim 1 , further comprising:

predicting aortic stiffness of the subject using the output indicative of the CFPWV of the subject.

12 . The method of claim 1 , further comprising:

predicting risk of the subject for developing any of hypertension, diabetes, obesity, myocardial infarction, heart failure, stroke, kidney disease, cognitive impairment and dementia using the output indicative of the CFPWV of the subject.

13 . The method of claim 1 , wherein the corresponding output indicative of the CFPWV of the subject indicates normalized CFPWV (nCFPWV).

14 . A system, comprising:

at least one computer hardware processor; and

at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform a method for using a machine learning model to estimate an indication of carotid-femoral pulse wave velocity (CFPWV) and/or vascular age (VA) of a subject from an arterial waveform previously measured at a single site by an arterial waveform acquisition device coupled to the subject, the method comprising:

obtaining the arterial waveform, the arterial waveform comprising a plurality of portions corresponding to a respective plurality of heartbeats of the subject, the plurality of portions comprising at least 10 portions, each of the plurality of portions comprising at least 250 data points;

generating a representative heartbeat waveform from the arterial waveform, the generating comprising:

detecting the plurality of portions in the arterial waveform;

individually detrending each of the detected plurality of portions to obtain a plurality of detrended portions,

averaging portions in the plurality of detrended portions to obtain the representative heartbeat waveform; and

processing the representative heartbeat waveform and at least one derivative waveform of the representative heartbeat waveform using a trained one-dimensional (1D) convolutional neural network (CNN) model to produce a corresponding output indicative of the CFPWV of the subject,

wherein the 1D CNN comprises multiple 1D convolutional layers, multiple rectified linear unit layers, multiple pooling layers, and a fully-connected layer,

wherein the 1D CNN comprises at least one million parameters, and

wherein the processing comprises calculating the output indicative of the CFPWV from the representative heartbeat waveform the at least one derivative waveform and the at least one million parameters.

15 . The system of claim 14 , wherein the corresponding output indicative of the CFPWV of the subject indicates normalized CFPWV (nCFPWV).

16 . The system of claim 14 , wherein the plurality of portions comprises at least 100 portions corresponding to a respective plurality of heart beats, and wherein each portion of the plurality of portions comprises at least 500 data points.

17 . The system of claim 14 , wherein the method further comprises:

predicting vascular age (VA) of the subject using a linear regression model different from the trained machine learning model and the output indicative of the CFPWV of the subject; and/or

predicting aortic stiffness of the subject using the output indicative of the CFPWV of the subject.

18 . At least one non-transitory computer readable storage medium storing processor-executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method for using a machine learning model to estimate an indication of carotid-femoral pulse wave velocity (CFPWV) and/or vascular age (VA) of a subject from an arterial waveform previously measured at a single site by an arterial waveform acquisition device coupled to the subject, the method comprising:

obtaining the arterial waveform, the arterial waveform comprising a plurality of portions corresponding to a respective plurality of heartbeats of the subject, the plurality of portions comprising at least 10 portions, each of the plurality of portions comprising at least 250 data points;

generating a representative heartbeat waveform from the arterial waveform, the generating comprising:

detecting the plurality of portions in the arterial waveform;

individually detrending each of the detected plurality of portions to obtain a plurality of detrended portions,

averaging portions in the plurality of detrended portions to obtain the representative heartbeat waveform; and

processing the representative heartbeat waveform and at least one derivative waveform of the representative heartbeat waveform using a trained one-dimensional (1D) convolutional neural network (CNN) model to produce a corresponding output indicative of the CFPWV of the subject,

wherein the 1D CNN comprises multiple 1D convolutional layers, multiple rectified linear unit layers, multiple pooling layers, and a fully-connected layer, wherein the 1D CNN comprises at least one million parameters, and

wherein the processing comprises calculating the output indicative of the CFPWV from the representative heartbeat waveform the at least one derivative waveform and the at least one million parameters.

19 . The at least one non-transitory computer readable storage medium of claim 18 , wherein the plurality of portions comprises at least 100 portions corresponding to a respective plurality of heart beats, and wherein each portion of the plurality of portions comprises at least 500 data points.

20 . The at least one non-transitory computer readable storage medium of claim 18 , wherein the method further comprises:

predicting vascular age (VA) of the subject using a linear regression model different from the trained machine learning model and the output indicative of the CFPWV of the subject; and/or

predicting aortic stiffness of the subject using the output indicative of the CFPWV of the subject.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 22, 2023
From: MITCHELL, GARY F.; GOTAL, JOHN D.
To: CARDIOVASCULAR ENGINEERING, INC.
Reel/Frame 064027/0970 →
Continuity (2)
Provisional Application 63343377 · May 18, 2022
Related Publication 20230371827A1 · Nov 23, 2023
References Cited (43)
US 20130310700A1 · Wiard et al. · 2013 [cited by applicant]
US 20140187883A1 · Lisogurski · 2014 [cited by applicant]
US 20160089042A1 · Saponas et al. · 2016 [cited by applicant]
US 20170014032A1 · Khair · 2017 [cited by applicant]
US 20180177459A1 · Eletr et al. · 2018 [cited by applicant]
US 20190076034A1 · Mori et al. · 2019 [cited by applicant]
US 20250169700A1 · Mitchell · 2025 [cited by examiner]
Bahloul et al., A multilayer perceptron-based carotid-to-femoral pulse wave velocity estimation using PPG signal. 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI). Jul. 2021. 6 pages. [cited by applicant]
Baldo et al., Carotid-femoral pulse wave velocity in a healthy adult sample: The ELSA-Brasil study. International journal of cardiology. Jan. 15, 2018;251:90-5. [cited by applicant]
Dall'Olio et al., Prediction of vascular aging based on smartphone acquired PPG signals. Scientific reports. Nov. 12, 2020;10(1):19756. 10 pages. [cited by applicant]
Jin et al., Estimating pulse wave velocity from the radial pressure wave using machine learning algorithms. Plos One. Jun. 28, 2021;16(6):e0245026. 16 pages. [cited by applicant]
Jin, Cardiovascular function assessment using computational blood flow modelling and machine learning. Doctoral dissertation. King's College London. Apr. 2021. 232 pages. [cited by applicant]
Mejia-Mejia et al., Photoplethysmography signal processing and synthesis. Photoplethysmography. Elsevier. 2021. 52 pages. [cited by applicant]
Mitchell et al., Vascular age assessed from an uncalibrated, noninvasive pressure waveform by using a deep learning approach: the AI-VascularAge model. Hypertension. Jan. 2024;81(1):193-201. Author Manuscript. 19 pages. [cited by applicant]
Mitchell, Arterial stiffness in aging: Does it have a place in clinical practice? Recent advances in hypertension. Hypertension. Mar. 3, 2021;77(3):768-80. [cited by applicant]
Saugel et al., Cardiac output estimation using pulse wave analysis—physiology, algorithms, and technologies: a narrative review. British journal of anaesthesia. Jan. 1, 2021;126(1):67-76. [cited by applicant]
Agbaje et al., Effect of arterial stiffness and carotid intima-media thickness progression on the risk of dysglycemia, insulin resistance, and dyslipidemia: a temporal causal longitudinal study. Hypertension. Mar. 2022;… [cited by applicant]
Agbaje et al., Effects of arterial stiffness and carotid intima-media thickness progression on the risk of overweight/obesity and elevated blood pressure/hypertension: a cross-lagged cohort study. Hypertension. Jan. 202… [cited by applicant]
Avolio et al., Arterial blood pressure measurement and pulse wave analysis-their role in enhancing cardiovascular assessment. Physiological measurement. Nov. 26, 2009;31(1):R1. [cited by applicant]
Ben-Shlomo et al., Aortic pulse wave velocity improves cardiovascular event prediction: an individual participant meta-analysis of prospective observational data from 17,635 subjects. Journal of the American College of … [cited by applicant]
Bikia et al., Leveraging the potential of machine learning for assessing vascular ageing: state- of-the-art and future research. European Heart Journal-Digital Health. Dec. 1, 2021;2(4):676-90. [cited by applicant]
Boutouyrie et al., Arterial stiffness and cardiovascular risk in hypertension. Circulation research. Apr. 2, 2021;128(7):864-86. [cited by applicant]
Cohen et al., Arterial stiffness and diabetes risk in Framingham Heart Study and UK Biobank. Circulation research. Sep. 2, 2022;131(6):545-54. [cited by applicant]
Frankel et al., Resistin, adiponectin, and risk of heart failure: the Framingham offspring study. Journal of the American College of Cardiology. Mar. 3, 2009;53(9):754-62. [cited by applicant]
Harris et al., Age, gene/environment susceptibility—Reykjavik Study: multidisciplinary applied phenomics. American journal of epidemiology. Author Manuscript. Available in PMC Aug. 10, 2009 (Published in final edited fo… [cited by applicant]
Huttunen et al., Deep learning for prediction of cardiac indices from photoplethysmographic waveform: a virtual database approach. International Journal for Numerical Methods in Biomedical Engineering. Mar. 2020;36(3):e… [cited by applicant]
Kaess et al., Aortic stiffness, blood pressure progression, and incident hypertension. Jama. Sep. 5, 2012;308(9):875-81. [cited by applicant]
Kannel et al., An investigation of coronary heart disease in families: the Framingham Offspring Study. American journal of epidemiology, historical article (Sep. 1, 1979;110(3):281-90). Jun. 1, 2017;185(11). [cited by applicant]
Kotchen, Historical trends and milestones in hypertension research: a model of the process of translational research. Hypertension. Oct. 2011;58(4):522-38. [cited by applicant]
Li et al., Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks. arXiv preprint arXiv:1903.11680. Jul. 3, 2019. 37 pages. [cited by applicant]
Mitchell et al., Arterial stiffness and cardiovascular events: the Framingham Heart Study. Circulation. Feb. 2, 2010;121(4):505-11. [cited by applicant]
Mitchell et al., Hemodynamic correlates of blood pressure across the adult age spectrum: noninvasive evaluation in the Framingham Heart Study. Circulation. Oct. 5, 2010;122(14):1379-86. [cited by applicant]
Mitchell, Aortic stiffness, pressure and flow pulsatility, and target organ damage. Journal of applied physiology. Dec. 1, 2018;125(12):1871-80. [cited by applicant]
Quan et al., The sleep heart health study: design, rationale, and methods. Sleep. Dec. 1, 1997;20(12):1077-85. [cited by applicant]
Rolnick et al., Deep learning is robust to massive label noise. arXiv preprint arXiv:1705.10694. Feb. 26, 2018. 10 pages. [cited by applicant]
Shin et al., Photoplethysmogram based vascular aging assessment using the deep convolutional neural network. Scientific Reports. Jul. 5, 2022;12(1):11377. 10 pages. [cited by applicant]
Splansky et al., The third generation cohort of the National Heart, Lung, and Blood Institute's Framingham Heart Study: design, recruitment, and initial examination. American journal of epidemiology. Jun. 1, 2007;165(11… [cited by applicant]
Sturlaugsdottir et al., Prevalence and determinants of carotid plaque in the cross-sectional REFINE-Reykjavik study. BMJ open. Nov. 1, 2016;6(11):e012457. 10 pages. [cited by applicant]
Vasan et al., Arterial stiffness and long-term risk of health outcomes: the Framingham Heart Study. Hypertension. May 2022;79(5):1045-56. [cited by applicant]
Westerhof et al., Normalized input impedance and arterial decay time over heart period are independent of animal size. American Journal of Physiology—Regulatory, Integrative and Comparative Physiology. Jul. 1, 1991;261(… [cited by applicant]
Hossain et al., Derivation and validation of gray-box models to estimate noninvasive in-vivo percentage glycated hemoglobin using digital vol. pulse waveform. Scientific reports. Jun. 9, 2021;11(1):12169. [cited by applicant]
Kagiyama et al., Machine learning assessment of left ventricular diastolic function based on electrocardiogramnal of the American College of Cardiology. Aug. 25, 2020;76(8):930-41. [cited by applicant]
Song et al., Serum cystatin C is related to pulse wave velocity even in subjects with normal serum creatinine. Hypertension Research. Oct. 2008;31(10):1895-902. [cited by applicant]