Abstract

Software-based blood pressure (BP) measurement offers non-invasive, continuous, real-time monitoring compared to traditional methods. This study explores a non-invasive machine learning approach to estimate arterial BP from ECG and SpO2 signals, using intra-arterial catheter BP readings as ground truth. A random forest (RF) algorithm was trained on a large dataset (~30 M beats, ~400 patient days), using extracted signal morphological features and patient characteristics. The RF model achieved low mean absolute error (MAE) for systolic/diastolic BP (4.29 ± 5.00 mmHg/2.38 ± 3.25 mmHg), independent of gender and race. Personalized models further improved performance (MAE: 3.51 ± 4.24 mmHg/1.85 ± 2.60 mmHg). We assessed different ECG lead combinations for estimating BP and observed that two limb leads, or a precordial lead were sufficient for an estimation below 5 mmHg MAE. These findings highlight the potential of real-time, personalized BP monitoring for early detection of hypertension, enhancing healthcare accessibility through non-invasive, continuous monitoring.

Details

Title
Machine learning based, subject-specific, gender and race independent, non-invasive estimation of the arterial blood pressure
Author
Sevakula, Rahul Kumar 1 ; Bota, Patrícia J. 1 ; Kassab, Mohamad B. 1 ; Bollepalli, Sandeep Chandra 1 ; Thambiraj, Geerthy 1 ; Boyer, Richard 2 ; Isselbacher, Eric M. 3 ; Armoundas, Antonis A. 4 

 Cardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA (ROR: https://ror.org/002pd6e78) (GRID: grid.32224.35) (ISNI: 0000 0004 0386 9924) 
 Anesthesia Department, Massachusetts General Hospital, Boston, MA, USA (ROR: https://ror.org/002pd6e78) (GRID: grid.32224.35) (ISNI: 0000 0004 0386 9924) 
 Healthcare Transformation Lab, Massachusetts General Hospital, Boston, MA, USA (ROR: https://ror.org/002pd6e78) (GRID: grid.32224.35) (ISNI: 0000 0004 0386 9924) 
 Cardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA (ROR: https://ror.org/002pd6e78) (GRID: grid.32224.35) (ISNI: 0000 0004 0386 9924); Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, USA (ROR: https://ror.org/042nb2s44) (GRID: grid.116068.8) (ISNI: 0000 0001 2341 2786) 
Pages
41
Section
Article
Publication year
2025
Publication date
Dec 2025
Publisher
Nature Publishing Group
e-ISSN
29482836
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3235539124
Copyright
© The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by/4.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.