Noninvasive estimation of aortic hemodynamics and cardiac contractility using machine learning
Vasiliki Bikia1, Theodore G Papaioannou2, Stamatia Pagoulatou3
1Laboratory of Hemodynamics and Cardiovascular Technology, Swiss Federal Institute of Technology, MED 3.2922, 1015, Lausanne, Switzerland. vasiliki.bikia@epfl.ch.
Insights
Noninvasive estimation of aortic systolic pressure and cardiac output is feasible using cuff pressure and pulse wave velocity. However, cardiac contractility (Ees) requires ejection fraction data for accurate prediction.
Area of Science:
- Cardiovascular Physiology
- Biomedical Engineering
- Medical Diagnostics
Background:
- Noninvasive estimation of aortic hemodynamics and cardiac contractility remains a significant challenge in cardiovascular disease detection.
- Accurate assessment of parameters like aortic systolic pressure (aSBP), cardiac output (CO), and end-systolic elastance (Ees) is crucial.
Purpose of the Study:
- To investigate the potential of estimating aSBP, CO, and Ees using noninvasive cuff-pressure and pulse wave velocity (PWV) measurements.
- To assess the added value of ejection fraction (EF) for improving Ees estimation.
Main Methods:
- Regression analysis employing machine learning models (Random Forest, SVR, Ridge, Gradient Boosting).
- Model training and validation using synthetic data (n=4,018) from an in-silico model.
- Comparison of model-derived aSBP with in-vivo measurements (n=783).
Main Results:
- Noninvasive aSBP and CO were estimated with acceptable accuracy (RMSEs 3.36% and 7.60%, respectively).
- Ees estimation from pressure signals alone showed poor performance (RMSE 16.96%).
- Incorporating EF significantly improved Ees prediction accuracy (RMSE 7.00%).
- In-vivo validation showed satisfactory accuracy for model-derived aSBP (RMSE 5.26%).
Conclusions:
- Noninvasive pressure measurements can accurately estimate aSBP and CO.
- Ees cannot be reliably predicted from pressure signals alone; EF is essential for improvement.
- This methodology shows promise for enhanced noninvasive monitoring of cardiovascular function.
Abstract:
Cardiac and aortic characteristics are crucial for cardiovascular disease detection. However, noninvasive estimation of aortic hemodynamics and cardiac contractility is still challenging. This paper investigated the potential of estimating aortic systolic pressure (aSBP), cardiac output (CO), and end-systolic elastance (Ees) from cuff-pressure and pulse wave velocity (PWV) using regression analysis. The importance of incorporating ejection fraction (EF) as additional input for estimating Ees was also assessed. The models, including Random Forest, Support Vector Regressor, Ridge, Gradient Boosting, were trained/validated using synthetic data (n = 4,018) from an in-silico model. When cuff-pressure and PWV were used as inputs, the normalized-RMSEs/correlations for aSBP, CO, and Ees (best-performing models) were 3.36 ± 0.74%/0.99, 7.60 ± 0.68%/0.96, and 16.96 ± 0.64%/0.37, respectively. Using EF as additional input for estimating Ees significantly improved the predictions (7.00 ± 0.78%/0.92). Results showed that the use of noninvasive pressure measurements allows estimating aSBP and CO with acceptable accuracy. In contrast, Ees cannot be predicted from pressure signals alone. Addition of the EF information greatly improves the estimated Ees. Accuracy of the model-derived aSBP compared to in-vivo aSBP (n = 783) was very satisfactory (5.26 ± 2.30%/0.97). Future in-vivo evaluation of CO and Ees estimations remains to be conducted. This novel methodology has potential to improve the noninvasive monitoring of aortic hemodynamics and cardiac contractility.
