Objective: We present a novel pipeline that consists of various algorithms for the estimation of the cardiac output (CO) during ventricular assist devices (VADs) support using a single pump inlet pressure (PIP) sensor as well as pump intrinsic signals.
Methods: A machine learning (ML) model was constructed for the prediction of the aortic valve opening status. When a closed aortic valve is detected, the estimated CO equals the estimated pump flow. Otherwise, the estimated CO equals the sum of the estimated pump flow and the aortic valve flow, estimated via a Kalman-filter approach. Both the pathophysiological conditions and the pump speed of an in-vitro test bench were adjusted in various combinations to evaluate the performance of the pipeline, as well as the individual estimators.
Results: The ML model yielded a Matthews correlation coefficient of 0.771, a sensitivity of 0.913 and a specificity of 0.871. An overall CO root mean square error (RMSE) of 0.69 L/min was achieved. Replacing the pump flow and aortic pressure estimators with sensors would decrease the RMSE below 0.5 L/min.
Conclusion: The performance of the proposed pipeline is considered the state of the art for VADs with an integrated PIP sensor. The effect of the individual estimators on the overall performance of the pipeline was thoroughly investigated and their limitations were identified for future research.
Significance: The clinical application of the proposed solution could provide the clinicians with essential information about the interaction between the patient's heart and the VAD to further improve the VAD therapy.