A Deep Reinforcement Learning-Optimized Blood Flow Profile for Enhanced Oxygenation Efficiency in Membrane Oxygenators
Open Access
Abstract
The membrane oxygenator serves as the core component of extracorporeal life support systems, and its gas exchange efficiency critically influences clinical outcomes. However, gas transfer is predominantly limited by the diffusion barrier within the blood-side boundary layer, where saturated red blood cells accumulate. Current research focuses mainly on static approaches such as optimizing fiber bundle configuration to promote passive blood mixing or modifying material properties, which are fixed after fabrication. In contrast, dynamic blood flow control remains an underexplored avenue for enhancing oxygenator performance. This study proposes an active pulsatile flow control method that disrupts the boundary layer barrier by optimizing periodic flow profiles, thereby directly improving gas exchange. A deep reinforcement learning framework integrating proximal policy optimization and long short-term memory networks was developed to autonomously search for optimal flow waveforms under constant flow conditions. A simplified stacked-plate membrane oxygenator was specially designed as the experimental platform to minimize flow path interference. Experimental results demonstrate that the optimized pulsatile profile increases the oxygen transfer rate by without compromising hemocompatibility.
Keywords
Funding Information
- National Natural Science Foundation of China (32171357)
- National Key Research and Development Program of China (2022YFC2402601)
This publication has 47 references indexed in Scilit:
- Nonlinear hemodynamics modeling of fractional Jeffery ternary hybrid nanofluid flow in multi-stenosed arteries with ANN-based simulationNonlinear Dynamics, 2025
- Effect of Pulsatile Blood Flow Parameters on Membrane Oxygenator Performance: A Cross‐Scale Simulation StudyInternational Journal for Numerical Methods in Biomedical Engineering, 2025
- Cycle ergometers in extracorporeal membrane oxygenation patient rehabilitation: A scoping reviewAustralian Critical Care, 2025
- Numerical modeling of pulsatile blood flow in the pulmonary artery under the influence of pulmonary hypertension and concomitant pathologiesInternational Communications in Heat and Mass Transfer, 2025
- A Novel Valveless Pulsatile Flow Pump for Extracorporeal Blood CirculationAnnals of Biomedical Engineering, 2025
- Comparison of hemodynamic features and thrombosis risk of membrane oxygenators with different structures: A numerical studyComputers in Biology and Medicine, 2023
- Active control of flow past an elliptic cylinder using an artificial neural network trained by deep reinforcement learningApplied Mathematics and Mechanics, 2022
- Deep reinforcement learning in fluid mechanics: A promising method for both active flow control and shape optimizationJournal of Hydrodynamics, 2020
- Effects of Hollow Fiber Membrane Oscillation on an Artificial LungAnnals of Biomedical Engineering, 2018
- Extracorporeal Membrane Oxygenation for Primary Graft Dysfunction After Lung Transplantation: Analysis of the Extracorporeal Life Support Organization (ELSO) RegistryThe Journal of Heart and Lung Transplantation, 2007