Transforming Smart Healthcare Systems with AI-Driven Edge Computing for Distributed IoMT Networks.

Area of Science:

• Computer Science
• Artificial Intelligence
• Healthcare Technology

Background:

• The Internet of Medical Things (IoMT) enables smart healthcare systems (SHM) through connected devices and edge computing.
• Existing IoMT solutions often neglect dynamic adaptation to public infrastructure and efficient data processing on constrained devices.
• Challenges include uneven load distribution and reduced system responsiveness in critical healthcare scenarios.

Purpose of the Study:

• To propose a lightweight, AI-driven edge computing model for enhanced smart healthcare systems.
• To improve the learning capabilities and anomaly detection in distributed IoMT networks.
• To address the limitations of existing approaches in dynamic healthcare environments.

Main Methods:

• Development of an AI-driven model integrating edge computing for IoMT.
• Implementation of efficient network anomaly detection algorithms for distributed environments.
• Verification and testing through simulations using synthetic data.

Main Results:

• The proposed model demonstrated significant improvements compared to related solutions.
• Achieved a 53% reduction in energy consumption.
• Reduced latency by 46%, packet loss rate by 52%, and overhead by 48%.
• Increased network throughput by 56%.

Conclusions:

• The AI-driven edge computing model offers an innovative and efficient solution for smart healthcare.
• The model effectively detects network anomalies in IoMT without additional system overhead.
• Results validate the model's efficacy in improving energy consumption, latency, packet loss, throughput, and overhead.