Striking the Privacy-Model Training Balance: A Case Study Using PERACTIV Device

In recent years, the healthcare industry has witnessed a surge in the adoption of wearable devices, transforming how individuals manage their well-being. This paper explores the intersection of healthcare technology, data protection, and the evolving regulatory landscape. It emphasizes the critical importance of preserving user data privacy and introduces different privacy-preserving solutions. The paper delves into various Federated Learning techniques, focusing on Federated Transfer Learning (FTL), and presents a practical application for medication adherence using the PERACTIV wrist-worn device. The proposed framework safeguards sensitive information, enabling a personalized and effective healthcare experience while addressing the challenges of medication non-adherence.