Tailoring Graph Neural Network-based Flow-guided Localization to Individual Bloodstreams and Activities

TL;DR

This paper enhances flow-guided localization using Graph Neural Networks by adapting to individual patient differences in bloodstreams and activities, improving continuous monitoring and early disease detection.

Contribution

It introduces a GNN adaptation pipeline based on physiological indicators to address individual variability in bloodstreams and activities.

Findings

Adaptations improve localization accuracy across diverse patients.

The approach enables continuous monitoring despite physiological differences.

Results show better handling of activity-related changes in blood flow.

Abstract

Flow-guided localization using in-body nanodevices in the bloodstream is expected to be beneficial for early disease detection, continuous monitoring of biological conditions, and targeted treatment. The nanodevices face size and power constraints that produce erroneous raw data for localization purposes. On-body anchors receive this data, and use it to derive the locations of diagnostic events of interest. Different Machine Learning (ML) approaches have been recently proposed for this task, yet they are currently restricted to a reference bloodstream of a resting patient. As such, they are unable to deal with the physical diversity of patients' bloodstreams and cannot provide continuous monitoring due to changes in individual patient's activities. Toward addressing these issues for the current State-of-the-Art (SotA) flow-guided localization approach based on Graph Neural Networks (GNNs), we propose a pipeline for GNN adaptation based on individual physiological indicators including height, weight, and heart rate. Our results indicate that the proposed adaptions are beneficial in reconciling the individual differences between bloodstreams and activities.