MD-ViSCo: A Unified Model for Multi-Directional Vital Sign Waveform Conversion

TL;DR

This paper introduces MD-ViSCo, a unified deep learning framework that can generate various vital sign waveforms from any single input, simplifying models needed for healthcare monitoring.

Contribution

The paper presents a novel multi-directional model using a shallow U-Net with Swin Transformer and AdaIN, capable of generating multiple vital waveforms with a single architecture.

Findings

Outperforms state-of-the-art baselines in waveform generation accuracy.

Achieves lower MAE and higher Pearson correlation across waveform types.

Generated ABP waveforms meet clinical standards and outperform baselines.

Abstract

Despite the remarkable progress of deep-learning methods generating a target vital sign waveform from a source vital sign waveform, most existing models are designed exclusively for a specific source-to-target pair. This requires distinct model architectures, optimization procedures, and pre-processing pipelines, resulting in multiple models that hinder usability in clinical settings. To address this limitation, we propose the Multi-Directional Vital-Sign Converter (MD-ViSCo), a unified framework capable of generating any target waveform such as electrocardiogram (ECG), photoplethysmogram (PPG), or arterial blood pressure (ABP) from any single input waveform with a single model. MD-ViSCo employs a shallow 1-Dimensional U-Net integrated with a Swin Transformer that leverages Adaptive Instance Normalization (AdaIN) to capture distinct waveform styles. To evaluate the efficacy of MD-ViSCo, we conduct multi-directional waveform generation on two publicly available datasets. Our framework surpasses state-of-the-art baselines (NabNet & PPG2ABP) on average across all waveform types, lowering Mean absolute error (MAE) by 8.8% and improving Pearson correlation (PC) by 4.9% over two datasets. In addition, the generated ABP waveforms satisfy the Association for the Advancement of Medical Instrumentation (AAMI) criterion and achieve Grade B on the British Hypertension Society (BHS) standard, outperforming all baselines. By eliminating the need for developing a distinct model for each task, we believe that this work offers a unified framework that can deal with any kind of vital sign waveforms with a single model in healthcare monitoring.