A Deep Learning-Based Privacy-Preserving Model for Smart Healthcare in Internet of Medical Things Using Fog Computing

Area of Science:

• Biomedical Informatics
• Data Security
• Artificial Intelligence in Healthcare

Background:

• The COVID-19 pandemic highlighted the critical need for robust smart healthcare solutions and big data analytics in medicine.
• Conventional systems struggle with the volume of confidential biomedical data, necessitating cloud storage and sharing.
• Existing methods for securing textual biomedical data face challenges with delays and real-time processing.

Purpose of the Study:

• To propose a novel fog-enabled privacy-preserving model, named sanitizer, for securing biomedical data.
• To leverage deep learning, specifically a Convolutional Neural Network with Bidirectional-LSTM, for enhanced medical entity recognition.
• To improve the utility and security of shared biomedical data in cloud environments.

Main Methods:

• Development of a fog-enabled privacy-preserving model named sanitizer.
• Implementation of a deep learning architecture combining Convolutional Neural Network (CNN) and Bidirectional-LSTM.
• Application of the model for Medical Entity Recognition (MER) on textual biomedical data.

Main Results:

• The sanitizer model achieved high performance metrics: 91.14% recall, 92.63% precision, and 92% F1-score.
• Demonstrated superior performance compared to existing state-of-the-art models in privacy-preserving sanitization.
• Showcased a 28.77% improvement in utility preservation over current methods.

Conclusions:

• The proposed sanitizer model offers an effective solution for privacy-preserving biomedical data handling in smart healthcare.
• Deep learning, particularly the CNN-Bidirectional-LSTM architecture, significantly enhances Medical Entity Recognition and data security.
• The model addresses the limitations of conventional systems by providing real-time, secure, and utility-preserving data management.