Amplitude-Independent Machine Learning for PPG through Visibility Graphs and Transfer Learning

TL;DR

This paper presents a novel amplitude-independent PPG analysis framework using visibility graphs and transfer learning, enabling robust, generalisable predictions of vascular health metrics with minimal preprocessing.

Contribution

It introduces VGTL-net, a new framework combining graph theory and computer vision for amplitude-independent PPG analysis with minimal preprocessing.

Findings

Achieves state-of-the-art vascular ageing prediction.

Robust estimation of blood pressure waveforms.

Generalises well across datasets and tasks.

Abstract

Photoplethysmography (PPG) refers to the measurement of variations in blood volume using light and is a feature of most wearable devices. The PPG signals provide insight into the body's circulatory system and can be employed to extract various bio-features, such as heart rate and vascular ageing. Although several algorithms have been proposed for this purpose, many exhibit limitations, including heavy reliance on human calibration, high signal quality requirements, and a lack of generalisation. In this paper, we introduce a PPG signal processing framework that integrates graph theory and computer vision algorithms, to provide an analysis framework which is amplitude-independent and invariant to affine transformations. It also requires minimal preprocessing, fuses information through RGB channels and exhibits robust generalisation across tasks and datasets. The proposed VGTL-net achieves state-of-the-art performance in the prediction of vascular ageing and demonstrates robust estimation of continuous blood pressure waveforms.