Key result
An AI model incorporating pulse wave velocity and brachial blood pressures strongly correlated with invasive LVESP (R=0.994) and showed no significant bias (p=0.95) compared to standard estimates.
Why the study?
Common non-invasive methods estimating left ventricular end-systolic pressure from brachial cuff measurements do not account for arterial stiffness between the left ventricle and brachial artery.
Does an AI model incorporating PWV and other hemodynamic parameters improve the non-invasive prediction of invasive LVESP compared to standard BP-based estimates in an in-silico healthy cohort?
Does an AI model incorporating PWV and other hemodynamic parameters improve the non-invasive prediction of invasive LVESP compared to standard BP-based estimates in an in-silico healthy cohort?
An AI model incorporating pulse wave velocity and basic hemodynamics provides highly accurate, unbiased non-invasive estimates of left ventricular end-systolic pressure.
Answers are grounded in this paper and cite their sources.
May enable unbiased non-invasive LVESP estimation; leaves open clinical translation beyond in-silico healthy data.
Background Invasive left ventricular (LV) pressure-volume (PV) loops are considered the gold standard method to quantify LV physiology. Non-invasive methods to perform LV-PVLs have gained popularity and shown to be prognostic in heart failure. The most popular non-invasive measurement of ventriculo-arterial coupling (Ees/Ea), estimates LV end systolic pressure (ESP) using brachial cuff blood pressure (BP) measurements [1]. However, this method does not account for key factors which may affect the pressure waveform as it travels from the LV to the brachial artery; notably the stiffness of arterial segment between the LV and brachial artery, which naturally increases with ageing. Purpose To train an artificial-intelligence (AI) model to predict invasive LVESP from brachial BPs and other key haemodynamic parameters including carotid-femoral pulse wave velocity (PWV) – the gold-standard non-invasive measure of arterial stiffness – and compare it to commonly used estimates of LVESP: Systolic BP (SBP) x 0.9 (LVESP[SBP]) and 2/3 SBP + 1/3 diastolic BP (DBP) (LVESP[SBP+DBP]). Methods An in-silico dataset of philologically plausible, healthy patients spread across the lifespan was used for this analysis [2]. LVESP was calculated at the dicrotic notch on invasive aortic root pressure waveforms. 3838 individuals were eligible for inclusion in this study, 767 individuals served as the internal-external validation cohort. The remaining patients were then split 80:20 into training and test sets. Based on clinical relevance, brachial SBP; brachial DBP; PWV; HR; stroke volume; and age were selected to serve as inputs for a random forest machine learning model. Subsequently, the model was used to predict LVESP (LVESP[AI]) in the validation cohort. Finally, Pearson’s correlation and Bland-Altman analysis were used to compare invasive LVESP to LVESP[AI], LVESP[SBP], and LVESP[SBP+DBP]. Results The best performing model included SBP, DBP, HR, age, and PWV and could reliably predict LVESP (Root mean square error: 1.206). Notably, the coefficients for SBP (0.679) and DBP (0.327) were strikingly close to commonly used estimates. LVESP[AI] had a stronger correlation (R=0.994) with the invasive LVESP compared to the LVESP[SBP] (R=0.909) and LVESP[SBP+DBP] (R=0.908). Bland-Altman analysis showed LVESP[SBP] (Bias: -4.01 mmHg, p<0.001) and LVESP[SBP+DBP] (Bias: -0.91 mmHg, p<0.001) were significantly biased, and over-estimated true LVESP. LVESP[AI] displayed no significant bias (p=0.95). Conclusion Our novel, non-invasive, artificial-intelligence enabled quantification of LVESP has demonstrated that incorporating PWV and other key haemodynamic parameters alongside brachial BPs yields more representative and less-biased predictions of invasive LVESP. This builds upon existing methods enabling non-invasive pressure-volume loop characterisation of the LV, which can be used in research and clinical practice.
No takes yet. Share an insight, caveat, or question.
Dunn et al. (2025) studied Healthy (n=3,838). Artificial intelligence model (LVESP[AI]) vs. LVESP[SBP] and LVESP[SBP+DBP] was evaluated on Correlation and bias with invasive LVESP (R=0.994, p=0.95). An AI model incorporating pulse wave velocity and brachial blood pressures strongly correlated with invasive LVESP (R=0.994) and showed no significant bias (p=0.95) compared to standard estimates.
Synapse has enriched 10 related papers. Consider them for comparative context: