INN-PAR: Invertible Neural Network for PPG to ABP Reconstruction
This work addresses the need for accurate non-invasive blood pressure monitoring for early prevention of cardiovascular diseases, representing an incremental improvement over existing deep learning approaches.
The paper tackled the problem of reconstructing arterial blood pressure (ABP) from photoplethysmography (PPG) signals to enable non-invasive blood pressure monitoring, introducing an invertible neural network (INN-PAR) that prevents information loss and integrates signal gradients, resulting in significant outperformance over state-of-the-art methods in waveform reconstruction and BP measurement accuracy on benchmark datasets.
Non-invasive and continuous blood pressure (BP) monitoring is essential for the early prevention of many cardiovascular diseases. Estimating arterial blood pressure (ABP) from photoplethysmography (PPG) has emerged as a promising solution. However, existing deep learning approaches for PPG-to-ABP reconstruction (PAR) encounter certain information loss, impacting the precision of the reconstructed signal. To overcome this limitation, we introduce an invertible neural network for PPG to ABP reconstruction (INN-PAR), which employs a series of invertible blocks to jointly learn the mapping between PPG and its gradient with the ABP signal and its gradient. INN-PAR efficiently captures both forward and inverse mappings simultaneously, thereby preventing information loss. By integrating signal gradients into the learning process, INN-PAR enhances the network's ability to capture essential high-frequency details, leading to more accurate signal reconstruction. Moreover, we propose a multi-scale convolution module (MSCM) within the invertible block, enabling the model to learn features across multiple scales effectively. We have experimented on two benchmark datasets, which show that INN-PAR significantly outperforms the state-of-the-art methods in both waveform reconstruction and BP measurement accuracy. Codes can be found at: https://github.com/soumitra1992/INNPAR-PPG2ABP.