Testing an inverse modeling approach with gradient boosting regression for stroke volume estimation using patient thermodilution data

TL;DR

This paper introduces a new method for estimating stroke volume using machine learning and a 1-D circulation model, showing promising accuracy and faster computation for real-time clinical use.

Contribution

A novel inverse modeling approach using gradient boosting regression for accurate and efficient stroke volume estimation.

Findings

The method achieved a mean absolute error of 16 mL and a normalized RMSE of 21% compared to thermodilution.

Predicted stroke volume was slightly underestimated but showed a strong correlation (r = 0.7) with reference values.

The approach significantly reduced computational time, making it suitable for real-time clinical applications.

Abstract

Stroke volume (SV) is a major indicator of cardiovascular function, providing essential information about heart performance and blood flow adequacy. Accurate SV measurement is particularly important for assessing patients with heart failure, managing patients undergoing major surgeries, and delivering optimal care in critical settings. Traditional methods for estimating SV, such as thermodilution, are invasive and unsuitable for routine diagnostics. Non-invasive techniques, although safer and more accessible, often lack the precision and user-friendliness needed for continuous bedside monitoring. We developed a modified method for SV estimation that combines a validated 1-D model of the systemic circulation with machine learning. Our approach replaces the traditional optimization process developed in our previous work, with a regression method, utilizing an in silico-generated dataset of various hemodynamic profiles to create a gradient boosting regression-enabled SV estimator. This dataset accurately mimics the dynamic characteristics of the 1-D model, allowing for precise SV predictions without resource-intensive parameter adjustments. We evaluated our method against SV values derived from the gold standard thermodilution method in 24 patients. The results demonstrated that our approach provides a satisfactory agreement between the predicted and reference data, with a MAE of 16 mL, a normalized RMSE of 21%, a bias of −9.2 mL, and limits of agreement (LoA) of [−47, 28] mL. A correlation coefficient of r = 0.7 (p < 0.05) was reported, with the predicted SV slightly underestimated (68 ± 23 mL) in comparison to the reference SV (77 ± 26 mL). The significant reduction in computational time of our method for SV assessment should make it suitable for real-time clinical applications.

Figures