Privacy-Enhanced Mechanisms in AI- and Digital Twins-Based Health Applications: Trade-off between Privacy and Measurement Accuracy
IEEE Instrumentation & Measurement Magazine · 2026-11 · 29 (8) · 63-72
DOI: 10.1109/mim.2026.11224909 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Instrumentation & Measurement Magazine, 2026-11. Verfasst von Kyriaki Tsantikidou und 1 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben.
Abstract (Originalsprache)
Traditional healthcare has increasingly evolved by Artificial Intelligence (AI), Internet of Things (IoT) and Digital Twins technologies that rely on continuous collection and transmission. Trust is no longer only associated with protecting sensitive information, but also with ensuring that the data being processed remains reliable and accurate. Homomorphic Encryption (HE) has emerged as a promising solution for privacy preservation by allowing computations to be performed directly on encrypted data. Nevertheless, this ability introduces various challenges deriving from the algorithm's computations that can affect numerical precision, processing and communication efficiency. This paper investigates the influence of HE schemes on measurement accuracy in AI- and Digital Twin-based healthcare systems. It analyzes the challenges introduced by HE that affect measurement accuracy and overall system reliability. The paper also highlights a few recent solutions, emphasizing that trust in healthcare systems depends not only on security guarantees but also on the reliability of processed data.
Zitieren
APA
Tsantikidou, K., & Sklavos, N. (2026). Privacy-Enhanced Mechanisms in AI- and Digital Twins-Based Health Applications: Trade-off between Privacy and Measurement Accuracy. IEEE Instrumentation & Measurement Magazine, 29(8), 63-72. https://doi.org/10.1109/mim.2026.11224909
Vancouver
Tsantikidou K, Sklavos N. Privacy-Enhanced Mechanisms in AI- and Digital Twins-Based Health Applications: Trade-off between Privacy and Measurement Accuracy. IEEE Instrumentation & Measurement Magazine. 2026;29(8):63-72. doi:10.1109/mim.2026.11224909
BibTeX
@article{Tsantikidou2026,
author = {Tsantikidou, Kyriaki and Sklavos, Nicolas},
title = {Privacy-Enhanced Mechanisms in AI- and Digital Twins-Based Health Applications: Trade-off between Privacy and Measurement Accuracy},
journal = {IEEE Instrumentation & Measurement Magazine},
year = {2026},
volume = {29},
number = {8},
pages = {63--72},
doi = {10.1109/mim.2026.11224909}
}
EUVIMED