Rehabilitation Risk Management: Enabling Data Analytics with Quantified Self and Smart Home Data

Area of Science:

• Biomedical Engineering
• Health Informatics
• Rehabilitation Medicine

Background:

• Home-based rehabilitation is essential post-treatment for acute and chronic diseases.
• Current outpatient rehabilitation lacks medical supervision, increasing risks of non-compliance and hospital readmission.
• Effective remote monitoring technologies are needed to identify patient risks during home recovery.

Purpose of the Study:

• To analyze existing monitoring systems and technologies for potential application in rehabilitation.
• To explore the use of sensor technology from Quantified Self and Smart Homes for medical data analytics.
• To propose a roadmap for implementing sensor-based risk management in rehabilitation.

Main Methods:

• Review of state-of-the-art monitoring systems and technologies.
• Analysis of sensor data from consumer-grade Quantified Self and Smart Home devices.
• Development of a conceptual roadmap for data analytics in rehabilitation risk management.

Main Results:

• Consumer-grade sensor technologies offer viable options for collecting rehabilitation data.
• Medical data analytics can be applied to sensor data for risk identification.
• A conceptual framework for sensor-based rehabilitation risk management was developed.

Conclusions:

• Transferring consumer-grade sensor technology is feasible for remote rehabilitation monitoring.
• Data analytics on sensor data can enhance patient safety and outcomes.
• This approach can mitigate risks associated with unsupervised home rehabilitation.