Quantifying the influence of combined lung and kidney support using a cardiovascular model and sensitivity analysis-informed parameter identification

The combination of extracorporeal membrane oxygenation (ECMO) and continuous renal replacement therapy (CRRT) pose complex hemodynamic challenges in intensive care. In this study, a comprehensive lumped parameter model (LPM) is developed to simulate the cardiovascular system, incorporating ECMO and CRRT circuit dynamics. A parameter identification framework based on global sensitivity analysis (GSA) and multi-start gradient-based optimization was developed and tested on 30 clinical data points from eight veno-arterial ECMO patients. To demonstrate feasibility, the model is used to analyze nine CRRT-ECMO connection schemes under varying flow conditions for a single patient. Our results indicate that CRRT has a notable impact on the cardiovascular system, with changes in pulmonary artery pressure of up to 203 %, highly dependent on ECMO flow. The GSA enabled the systematic and agnostic identification of a subset of model parameters used in the calibration process. The established parameter estimation framework is fast and robust, as no manual tuning of algorithm parameters is required, and achieves high correlations between simulation and experimental data with R² > 0.98. It uses modeling methods that could pave the way for real-time applications in intensive care. This open-source framework provides a valuable tool for the systematic evaluation of combined ECMO and CRRT, which can be used to develop standardized treatment protocols and improve patient outcomes in critical care. This model provides a good basis for addressing research questions related to mechanical circulatory and respiratory support and presents tools to help move towards a digital twin in healthcare.