A LSTM-Transformer Model for pulsation control of pVADs

2025-03-10

AI Summary

Precise pulsatile flow regulation in implantable pulsatile ventricular assist devices (pVADs) remains challenging, particularly under conditions of limited training data and high physiological noise, compromising control robustness. Method: This study proposes the AP-pVAD model—a novel synergistic control framework integrating mechanism-based NPQ modeling with an LSTM-Transformer hybrid neural network. It pioneers the incorporation of Transformer’s attention mechanism into LSTM to enable high-accuracy dynamic prediction of critical pulsatile timing points; the NPQ component ensures physical interpretability, while the hybrid architecture enhances generalization. Results: Experimental evaluation demonstrates a maximum pressure prediction error of only 2.15 mmHg and a pulsatile timing-point error as low as 1.78 ms. In vivo animal validation shows significant improvement in aortic pressure and sustained device operation for over 27 hours with continuous survival, establishing a new paradigm for clinical reliability of pVADs.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Behavior Learning & Control
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Methods: A method of the pulsation for a pVAD is proposed (AP-pVAD Model). AP-pVAD Model consists of two parts: NPQ Model and LSTM-Transformer Model. (1)The NPQ Model determines the mathematical relationship between motor speed, pressure, and flow rate for the pVAD. (2)The Attention module of Transformer neural network is integrated into the LSTM neural network to form the new LSTM-Transformer Model to predict the pulsation time characteristic points for adjusting the motor speed of the pVAD. Results: The AP-pVAD Model is validated in three hydraulic experiments and an animal experiment. (1)The pressure provided by pVAD calculated with the NPQ Model has a maximum error of only 2.15 mmHg compared to the expected values. (2)The pulsation time characteristic points predicted by the LSTM-Transformer Model shows a maximum prediction error of 1.78ms, which is significantly lower than other methods. (3)The in-vivo test of pVAD in animal experiment has significant improvements in aortic pressure. Animals survive for over 27 hours after the initiation of pVAD operation. Conclusion: (1)For a given pVAD, motor speed has a linear relationship with pressure and a quadratic relationship with flow. (2)Deep learning can be used to predict pulsation characteristic time points, with the LSTM-Transformer Model demonstrating minimal prediction error and better robust performance under conditions of limited dataset sizes, elevated noise levels, and diverse hyperparameter combinations, demonstrating its feasibility and effectiveness.

Problem

• Develops a model to control pulsation in pVADs using LSTM-Transformer.
• Predicts pulsation time points with minimal error for motor speed adjustment.
• Validates model effectiveness through hydraulic and animal experiments.

Innovation

• LSTM-Transformer Model predicts pulsation time points.
• NPQ Model links motor speed, pressure, flow rate.
• AP-pVAD Model validated in hydraulic, animal experiments.