Time Series Models of the Human Heart in Patients with Heart Failure: Toward a Digital Twin Approach

Nilmini Wickramasinghe; Nalika Ulapane; Yuxin Zhang; Paul Jansons; Gunnar Cedersund; Ralph Maddison

doi:10.3390/s26010082

,

and

¹

School of Computing, Engineering & Mathematical Sciences, La Trobe University, Melbourne, VIC 3086, Australia

²

Faculty of Health, Deakin University, Melbourne, VIC 3125, Australia

³

Department of Biomedical Engineering (IMT), Linköping University, SE-581 83 Linköping, Sweden

^*

Authors to whom correspondence should be addressed.

Sensors2026, 26(1), 82;https://doi.org/10.3390/s26010082
(registering DOI)

This article belongs to the Special Issue Precision Health 2.0: Integrating Data from Wearables and AI for Next-Generation Personalized Care

Version Notes

Order Reprints

Review Reports

Abstract

Digital Twins (DTs) are digital replicas of physical entities. The use of DTs in healthcare is a growing area of research. With DTs, there is potential to revolutionize healthcare with the assistance of Artificial Intelligence. This can lead to achieving precision, personalization, and value addition in healthcare. Contributing to this field, we present one of the first attempts of uncovering time series models of decompensation of heart failure. This was performed using some of the first data collected from the pilot phase of the SmartHeart study, in which an at-home, wearable, wireless sensor-based digital self-monitoring system for people with heart failure was tested.

Keywords:

artificial intelligence; chronic disease; digital twin; heart failure; machine learning; personalized care; precision medicine; regression; time series; wearable sensors

Time Series Models of the Human Heart in Patients with Heart Failure: Toward a Digital Twin Approach

Abstract

Article Metrics

Citations

Article Access Statistics