DLSDHMS: Design of a deep learning-based analysis model for secure and distributed hospital management using...

Area of Science:

• Computer Science
• Artificial Intelligence
• Healthcare Informatics

Background:

• Existing hospital management systems are complex and lack deep learning integration.
• Mutable storage solutions in current models reduce trust in multi-patient scenarios.
• Efficient hospital management requires secure storage, alert systems, and staff/report management.

Purpose of the Study:

• To design a secure and distributed hospital management model using deep learning and context-aware sidechains.
• To overcome limitations of existing complex and less accurate hospital management systems.
• To enhance trust and efficiency in hospital data management.

Main Methods:

• Utilized an IoT network to collect data from hospital entities.
• Implemented context-sensitive sidechains for secure data storage (Medicine, Doctor, Insurance, Appointments).
• Optimized sidechains using Iterative Genetic Algorithm (IGA) and processed data with Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs).

Main Results:

• Reduced computational delay by 3.5% and storage costs by 8.3% compared to other blockchain deployments.
• Achieved 9.3% higher accuracy and 4.8% higher precision in preempting patient issues.
• Demonstrated improved storage and retrieval performance through IGA-based optimization.

Conclusions:

• The proposed deep learning model offers a secure, efficient, and accurate solution for hospital management.
• Context-aware sidechains and advanced AI techniques enhance data integrity and predictive capabilities.
• The model is suitable for real-time clinical deployments, improving disease preemption and patient outcomes.