A Differentially Privacy Assisted Federated Learning Scheme to Preserve Data Privacy for IoMT Applications

The rapid development of Artificial Intelligence (AI) has had a significant impact on various industries, including healthcare. The Internet of Medical Things (IoMT) has played a vital role in this evolution. However, while AI has contributed to many benefits in healthcare, concerns about data privacy and security persist. To address these concerns, we propose a framework that combines Federated Learning (FL) and Differential Privacy (DP) to enhance data protection within IoMT. By integrating FL’s decentralized approach with DP’s mechanism to prevent data reconstruction from model outputs, we can improve data confidentiality. This integrated approach is used to develop and analyze high-performing Convolutional Neural Networks (CNNs) for detecting Tuberculosis using chest X-ray datasets. The framework undergo thorough performance evaluation, utilizing various metrics to establish its superiority over baseline models. The results demonstrate the effectiveness of our framework as a robust solution for secure and private AI applications in healthcare.

I. Introduction

Over recent years, healthcare has swiftly shifted from a traditional specialist-centric to a patient-centric Smart Healthcare System (SHS), driven by technological advancements. AI techniques have shown promise in early chronic disease detection through biomedical image analytics, utilizing health data [1], [2]. The Internet of Medical Things (IoMT) crucially enhances SHS by elevating electronic device productivity and accuracy [3]. Technological progress has led to an unprecedented surge in individual health data, supported by IoT devices in medical environments [4]. IoMT facilitates machine learning and deep learning models by aggregating diverse device-generated data, aiding scenarios like pulse monitoring, auxiliary diagnoses, and disease prediction [5]. The foremost challenge facing the digital health revolution is privacy concerns [6], [7]. While healthcare entities seek data for product enhancement, preserving user privacy is paramount. A privacy-productivity deadlock exists: companies desire data for improvement and users demand privacy protection. A balance must be struck, acknowledging that some privacy trade-offs are inevitable. Without access to private healthcare data, advanced technologies’ implementation remains restricted. The focus should be on safeguarding the invaluable and vulnerable aspects, rather than fixating on absolute privacy.