Online cardiac output estimation during transvalvular left ventricular assistance

The intelligent Impella: Future perspectives of artificial intelligence in the setting of Impella support

AIMS

Artificial intelligence (AI) has emerged as a potential useful tool to support clinical treatment of heart failure, including the setting of mechanical circulatory support (MCS). Modern Impella pumps are equipped with advanced technology (SmartAssist), enabling real-time acquisition and display of data related to both pump performance and the patient's haemodynamic status. These data emerge as an 'ideal' source for data-driven AI applications to predict the clinical course of an ongoing therapeutic protocol. Yet, no evidence of effective application of AI tools in the setting of Impella support is available. On this background, we aimed at identifying possible future applications of AI-based tools in the setting of temporary MCS with an Impella device.

METHODS

We explored the state of research and development at the intersection of AI and Impella support and derived future potential applications of AI in routine Impella clinical management.

RESULTS

We identified different areas where the future implementation of AI tools may contribute to addressing important clinical challenges in the setting of Impella support, including (i) early identification of the best suited pathway of care according to patients' conditions at presentation and intention to treat, (ii) prediction of therapy outcomes according to different possible therapeutic actions, (iii) optimization of device implantation procedures and evaluation of proper pump position over the whole course of support and (iv) prevention and/or rationale management of haemocompatibility-related adverse events. For each of those areas, we discuss the potential advantages, challenges and implications of harnessing AI-driven insights in the setting of MCS with an Impella device.

CONCLUSIONS

Temporary MCS with an Impella device has great potential to benefit from the integration of AI-based tools. Such tools may indeed translate into groundbreaking innovation supporting clinical decision-making and therapy regulation, in particular in complex scenarios such as the multidevice MCS strategy.

An in silico analysis of unsteady flow structures in a microaxial blood pump under a pulsating rotation speed

BACKGROUND AND OBJECTIVE

Ventricular assist devices (VADs) are generally designed to perform continuous flow. However, it has been proven that continuous flow, which is not a physiological hemodynamic state, may cause severe complications such as gastrointestinal bleeding, pulmonary hypertension, and ventricular suction. For these reasons, many pulsating blood pump control strategies have been proposed and have the potential for application in percutaneous ventricular assist devices (pVADs) or microaxial blood pumps. A few cases report extra hemolysis when introducing pulsating speed, while none involve blood pumps. This research's primary purpose is to evaluate the potential hemolysis of pVAD under pulsating flow conditions.

METHODS

First, the pulsating flow state is deduced using a heart failure model and varying speed. The heart model is established according to the pathology state collected from a clinical check. The rotation speed and boundary physical state are set to fit the heart failure model. The computational fluid dynamics (CFD) method with the hemolysis prediction model is performed. Furthermore, we used proper orthogonal decomposition (POD) analysis to reconstruct the flow field and obtain more details about shearing and transporting effects.

RESULTS

(1) As a variable rotational speed was introduced, no significant gain in hemolysis accumulation appeared in pVAD. This is quite different from long-term implantable VADs. (2) Pulsation affects hemolysis mainly through pressure (or normal stress). Variable rotational speed affects hemolysis mainly through flow instability. (3) Variable rotational speed will increase the instability and influence hemolysis by transporting and shearing effects, while the transporting effect is more significant.

CONCLUSIONS

The unsteady flow state will affect the spatial distribution of hemolysis, which should be taken into account during control strategy and impeller shape design.

Pressure and Bernoulli-based Flow Measurement via a Tapered Inflow VAD Cannula

OBJECTIVE

Currently available ventricular assist devices provide continuous flow and do not adapt to the changing needs of patients. Physiological control algorithms have been proposed that adapt the pump speed based on the left ventricular pressure. However, so far, no clinically used pump can acquire this pressure. Therefore, for the validation of physiological control concepts in vivo, a system that can continuously and accurately provide the left ventricular pressure signal is needed.

METHODS

We demonstrate the integration of two pressure sensors into a tapered inflow cannula compatible with the HeartMate 3 (HM3) ventricular assist device. Selective laser melting was used to incorporate functional elements with a small footprint and therefore retain the geometry, function and implantability of the original cannula. The system was tested on a hybrid mock circulation system. Static and simulated physiological flow and pressure profiles were used to evaluate the combined pressure and flow sensing capabilities of the modified cannula.

CONCLUSION

The cannula prototypes enabled continuous pressure measurements at two points of their inner wall in the range of 100 and 200 mmHg. The developed, Bernoulli-based, two sensor model improved the accuracy of the measured simulated left ventricular pressure by eliminating the influence of flow inside the cannula. This method reduced the flow induced pressure uncertainty from up to 7.6 mmHg in single sensor measurements to 0.3 mmHg. Additionally, the two-sensor system and model enable the measurement of the blood flow through the pump with an accuracy of 0.140.04 L/min, without dedicated flow sensors.

Cardiac Output Estimation: Online Implementation for Left Ventricular Assist Device Support

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.

Model-Based Weaning Tests for VA-ECLS Therapy

Venoarterial extracorporeal life support (VA-ECLS) is used in ICUs (intensive care units) for the most extreme presentations of acute and severe cardiogenic shock, and one of the main issues the clinicians have to deal with is the weaning from VA-ECLS. In this study, a patient-specific model of the cardiovascular system connected to a VA-ECLS is built to improve the understanding of this complex system. Pig experiments are performed to validate the model, and the results are quite promising since the mean difference between experimental data and simulation is smaller than 5% for all the hemodynamic quantities. It is also a major objective of this paper to provide a proof-of-concept analysis that model-based approaches could improve the weaning strategy for VA-ECLS therapy.