Wearable health devices have rapidly entered society to transform healthcare monitoring systems which now provide patients with direct-time data collection for better medical treatments. The collection of health data alongside its processing and transmission creates major privacy and security obstacles because stable data protection systems should be developed to meet regulatory requirements along with optimizing computational performance. This paper introduces an AI-based privacy-protecting system for secure acquisition of health information from wearable devices in real-time. The proposed framework uses FL as well as HE and DP alongside Blockchain to create a security system that sustains decentralized operations with regulatory compliance features. The proposed framework makes use of device-native intelligence together with privacy-focused artificial intelligence models to deliver real-time analytics as it safeguards all patient-specific sensitive information. Research has demonstrated that AI-based privacy-preserving methods lead to superior performance than standard methods because they provide better data integrity while being faster and more compliant with regulations. The research adds value to secure healthcare analytics using AI by developing a new approach to wearable data management which satisfies scalability needs and follows regulatory standards.
Privacy-preserving AI, Secure health data collection, Wearable device security, Federated learning in healthcare, Real-time health monitoring
IRE Journals:
Maliha Zaman Nizum
"AI-Driven Privacy-Preserving Framework for Secure Real-Time Health Data Collection from Wearable Devices" Iconic Research And Engineering Journals Volume 8 Issue 9 2025 Page 425-439
IEEE:
Maliha Zaman Nizum
"AI-Driven Privacy-Preserving Framework for Secure Real-Time Health Data Collection from Wearable Devices" Iconic Research And Engineering Journals, 8(9)