Machine Learning Reconstruction of Left Ventricular Pressure From Peripheral Waveforms

Abstract

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.

Files

Additional details