# Remote patient monitoring using artificial intelligence: Current state, applications, and challenges

**Authors:** Thanveer Shaik, Xiaohui Tao, Niall Higgins, Lin Li, Raj Gururajan, Xujuan Zhou, U. Rajendra Acharya  
**arXiv:** [2301.10009](https://arxiv.org/abs/2301.10009)  
**Date:** 2023-01-19  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2301.10009v1/

## Key points

- The use of artificial intelligence (AI) in healthcare is rapidly increasing, with remote patient monitoring (RPM) being one of the most common applications.
- RPM systems assist doctors in monitoring patients with chronic or acute illnesses at remote locations, elderly people receiving in-home care, and even hospitalized patients.
- Conventional patient monitoring involves invasive approaches that require skin contact to monitor health status.
- AI-enabled RPM architectures have transformed healthcare monitoring applications because they can detect early deterioration in patients' health, personalize individual patient health parameter monitoring using federated learning techniques, and learn human behavior patterns using reinforcement learning methods.
- However, there are still challenges to adopting AI into RPM systems such as data privacy concerns and implementation issues.
- The future directions for AI in RPM applications are analyzed based on these challenges and trends.

## Summary

The use of artificial intelligence (AI) in healthcare is rapidly increasing, with remote patient monitoring (RPM) being one of the most common applications. RPM systems assist doctors in monitoring patients with chronic or acute illnesses at remote locations, elderly people receiving in-home care, and even hospitalized patients. The reliability of manual patient monitoring systems depends on staff time management. Conventional patient monitoring involves invasive approaches that require skin contact to monitor health status. This study provides a comprehensive review of RPM systems, including the advanced technologies adopted, the impact of AI on RPM, challenges and trends in AI-enabled RPM, and benefits and challenges of patient-centric RPM architectures enabled with Internet of Things wearable devices and sensors using cloud, fog, edge, and blockchain technologies. The role of AI in RPM ranges from physical activity classification to chronic disease monitoring and vital signs monitoring in emergency settings. The results show that AI-enabled RPM architectures have transformed healthcare monitoring applications because they can detect early deterioration in patients' health, personalize individual patient health parameter monitoring using federated learning techniques, and learn human behavior patterns using reinforcement learning methods. However, there are still challenges to adopting AI into RPM systems such as data privacy concerns and implementation issues. The future directions for AI in RPM applications are analyzed based on these challenges and trends. Overall this study highlights the potential benefits that can be achieved by integrating AI into remote patient monitoring systems while also identifying key areas where further research is needed to overcome existing challenges.