Machine Learning Reconstruction of Left Ventricular Pressure From Peripheral Waveforms

Background: Left ventricular (LV) pressure measurement is the clinical gold standard for assessing cardiac function; however, its reliance on invasive catheterization limits accessibility and widespread use. Objectives: This study aimed to develop a cuff-based machine learning (cuff-ML) approach for...

Full description

Saved in:
Bibliographic Details
Main Authors: Alessio Tamborini, PhD, Arian Aghilinejad, PhD, Ray V. Matthews, MD, Morteza Gharib, PhD
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:JACC: Advances
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772963X25005290
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226856793899008
author Alessio Tamborini, PhD
Arian Aghilinejad, PhD
Ray V. Matthews, MD
Morteza Gharib, PhD
author_facet Alessio Tamborini, PhD
Arian Aghilinejad, PhD
Ray V. Matthews, MD
Morteza Gharib, PhD
author_sort Alessio Tamborini, PhD
collection DOAJ
description Background: Left ventricular (LV) pressure measurement is the clinical gold standard for assessing cardiac function; however, its reliance on invasive catheterization limits accessibility and widespread use. Objectives: This study aimed to develop a cuff-based machine learning (cuff-ML) approach for reconstructing LV pressure from noninvasive brachial waveforms as a bedside assessment of cardiac function. Methods: Subjects referred for nonemergent left heart catheterization were recruited for LV pressure and brachial cuff waveform measurement. The cuff-ML method was trained using brachial waveforms to predict LV pressure and was evaluated for morphology and parameters accuracy against invasive catheter measurements. Cardiac function was assessed based on the reduced LV peak pressure derivative ([+]dP/dt <1,200 mm Hg/s). Results: A total of 104 subjects, comprising 3,572 simultaneous LV and cuff-based brachial waveform pairs, were analyzed using a 70:30 train-test split (test cohort: 32 subjects, 1,023 cardiac cycles). The cuff-ML approach demonstrated high accuracy in reconstructing LV waveform shape compared to catheter measurements (median normalized root mean squared error = 8.2%). Pressure-based parameters, including maximum pressure (r = 0.92, P < 0.001), mean blood pressure (r = 0.94, P < 0.001), and developed pressure (r = 0.85, P < 0.001), showed strong correlations with invasive measurements. Cuff-ML-reconstructed waveforms identified abnormal systolic contractility (72% sensitivity, 73% specificity) on a beat-to-beat basis. Conclusions: Cuff-ML accurately reconstructs LV pressure from brachial cuff measurements. This noninvasive approach may be helpful for assessment of cardiac function and requires further study.
format Article
id doaj-art-4aad0618ad0a4f259c4ab5816f5a3992
institution Kabale University
issn 2772-963X
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series JACC: Advances
spelling doaj-art-4aad0618ad0a4f259c4ab5816f5a39922025-08-24T05:15:34ZengElsevierJACC: Advances2772-963X2025-09-014910210410.1016/j.jacadv.2025.102104Machine Learning Reconstruction of Left Ventricular Pressure From Peripheral WaveformsAlessio Tamborini, PhD0Arian Aghilinejad, PhD1Ray V. Matthews, MD2Morteza Gharib, PhD3Department of Medical Engineering, California Institute of Technology, Pasadena, California, USA; Address for correspondence: Dr Alessio Tamborini, Department of Medical Engineering, California Institute of Technology, 1200 E California BLVD, Pasadena, California 91125, USA.Department of Medical Engineering, California Institute of Technology, Pasadena, California, USADivision of Cardiovascular Medicine, Keck School of Medicine, University of Southern California, Los Angeles, California, USADepartment of Medical Engineering, California Institute of Technology, Pasadena, California, USABackground: Left ventricular (LV) pressure measurement is the clinical gold standard for assessing cardiac function; however, its reliance on invasive catheterization limits accessibility and widespread use. Objectives: This study aimed to develop a cuff-based machine learning (cuff-ML) approach for reconstructing LV pressure from noninvasive brachial waveforms as a bedside assessment of cardiac function. Methods: Subjects referred for nonemergent left heart catheterization were recruited for LV pressure and brachial cuff waveform measurement. The cuff-ML method was trained using brachial waveforms to predict LV pressure and was evaluated for morphology and parameters accuracy against invasive catheter measurements. Cardiac function was assessed based on the reduced LV peak pressure derivative ([+]dP/dt <1,200 mm Hg/s). Results: A total of 104 subjects, comprising 3,572 simultaneous LV and cuff-based brachial waveform pairs, were analyzed using a 70:30 train-test split (test cohort: 32 subjects, 1,023 cardiac cycles). The cuff-ML approach demonstrated high accuracy in reconstructing LV waveform shape compared to catheter measurements (median normalized root mean squared error = 8.2%). Pressure-based parameters, including maximum pressure (r = 0.92, P < 0.001), mean blood pressure (r = 0.94, P < 0.001), and developed pressure (r = 0.85, P < 0.001), showed strong correlations with invasive measurements. Cuff-ML-reconstructed waveforms identified abnormal systolic contractility (72% sensitivity, 73% specificity) on a beat-to-beat basis. Conclusions: Cuff-ML accurately reconstructs LV pressure from brachial cuff measurements. This noninvasive approach may be helpful for assessment of cardiac function and requires further study.http://www.sciencedirect.com/science/article/pii/S2772963X25005290brachial cuffcatheterizationleft ventricular pressuremachine learningperipheral waveformstransfer function
spellingShingle Alessio Tamborini, PhD
Arian Aghilinejad, PhD
Ray V. Matthews, MD
Morteza Gharib, PhD
Machine Learning Reconstruction of Left Ventricular Pressure From Peripheral Waveforms
JACC: Advances
brachial cuff
catheterization
left ventricular pressure
machine learning
peripheral waveforms
transfer function
title Machine Learning Reconstruction of Left Ventricular Pressure From Peripheral Waveforms
title_full Machine Learning Reconstruction of Left Ventricular Pressure From Peripheral Waveforms
title_fullStr Machine Learning Reconstruction of Left Ventricular Pressure From Peripheral Waveforms
title_full_unstemmed Machine Learning Reconstruction of Left Ventricular Pressure From Peripheral Waveforms
title_short Machine Learning Reconstruction of Left Ventricular Pressure From Peripheral Waveforms
title_sort machine learning reconstruction of left ventricular pressure from peripheral waveforms
topic brachial cuff
catheterization
left ventricular pressure
machine learning
peripheral waveforms
transfer function
url http://www.sciencedirect.com/science/article/pii/S2772963X25005290
work_keys_str_mv AT alessiotamboriniphd machinelearningreconstructionofleftventricularpressurefromperipheralwaveforms
AT arianaghilinejadphd machinelearningreconstructionofleftventricularpressurefromperipheralwaveforms
AT rayvmatthewsmd machinelearningreconstructionofleftventricularpressurefromperipheralwaveforms
AT mortezagharibphd machinelearningreconstructionofleftventricularpressurefromperipheralwaveforms