Edge-Driven Disability Detection and Outcome Measurement in IoMT Healthcare for Assistive Technology.

Area of Science:

• Medical Informatics
• Computer Science
• Assistive Technology

Background:

• Edge computing (EC) and Internet of Medical Things (IoMT) integration enables adaptive healthcare.
• Real-time monitoring and personalized solutions are crucial for individuals with disabilities and chronic conditions.
• Untrusted devices in IoMT systems introduce communication delays and security risks.

Purpose of the Study:

• To present a Trust-Driven Disability-Detection Model Using Secured Random Forest Classification (TTDD-SRF).
• To address security risks and communication delays in EC-IoMT healthcare systems.
• To improve real-time health monitoring and disability detection for patients.

Main Methods:

• Developed the TTDD-SRF model integrating EC and IoMT for disability detection.
• Utilized secured Random Forest Classification with edge-level trust score computation.
• Focused on detecting abnormal movement patterns indicative of disability.

Main Results:

• The TTDD-SRF model demonstrated improved classification accuracy for abnormal motion detection.
• Enhanced data reliability through edge-level trust scores, reducing false positives.
• Achieved significant performance improvements: 48% network throughput, 42% system resilience, 49% device integrity, and 45% energy consumption reduction.

Conclusions:

• The TTDD-SRF model effectively enhances healthcare accessibility and monitoring for individuals with disabilities.
• The proposed paradigm improves decision-making accuracy in health-related applications, particularly disability detection.
• Highlights the potential of edge technologies in advancing assistive technology and medical systems.