A Quantum-Enhanced Secure Aggregation Framework for Federated Multi-Disease Prediction in IoMT Healthcare

Read full text Summarise with VIRAT
Authors: Baby Anusha Medisetty, M. S. Anbarasi
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The IoMT enables continuous health monitoring; however, integrating heterogeneous medical data introduces significant challenges in terms of security, privacy, and disease identification. Classical federated learning still remains vulnerable against inference attacks, as well as potential quantum-enabled adversaries despite some protective benefits. This work presents a Privacy-Preserving Quantum-AI Framework (PP-QAI) that facilitates secure multi-disease diagnosis in IoMT environments. The framework employs a quantum-secure aggregation mechanism that combines quantum key distribution with postquantum cryptography in order to safeguard model updates, as well as hybrid quantum-classical neural networks in order to achieve lightweight feature encoding on edge devices. In this paper, a multitask quantum-learning model is developed which jointly assesses ECG signals, physiological vitals, and EHR data for multi-disease prediction. Realistic IoMT constraints are introduced in the evaluation, including non-IID data distributions, heterogeneity of devices, and limited bandwidth. Experimental results reflect significant gains in privacy preservation and reductions in communication overhead, with improvements in diagnostic accuracy compared with traditional federated baselines. The proposed PP-QAI thus provides a scalable and secure foundation for next-generation smart healthcare systems.

Fields of Study & Subjects

Privacy-Preserving Technologies in Data IoT and Edge/Fog Computing Blockchain Technology Applications and Security

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
28 March 2026
Language
EN