Design and application of a novel telemedicine system jointly driven by multinetwork integration and remote control: Practical experience from PLAGH, China

Ruiqing Wang, Jie Zhang, Shilin He, Huayuan Guo, Li Tao, Qin Zhong, Jun Ma, Jie Xu, Kunlun HeHealthcare 2023 · DOI

TL;DR

This paper introduces a novel telemedicine system that tackles China's persistent challenges of unstable networks and difficult interconnections. By integrating multiple networks and employing a unique remote control method, the system achieves robust performance and high user satisfaction, paving the way for more accessible and efficient remote healthcare.

What Problem Does This Paper Address?

Telemedicine holds immense promise for bridging the gap in medical resource distribution, especially in vast countries like China where urban centers concentrate most healthcare facilities. However, existing telemedicine systems often suffer from poor network stability and difficulties in connecting diverse medical institutions. This can lead to unreliable data transmission, interrupted consultations, and a generally frustrating user experience. The authors aim to overcome these limitations by designing a telemedicine system that leverages multinetwork integration and a non-intrusive remote control mechanism, ensuring a stable, efficient, and user-friendly remote healthcare experience.

Methods

The core of the proposed system lies in two key innovations:

  • Multilink Aggregation Algorithm (MLA-BWV): This algorithm combines multiple network links (e.g., 4G from different carriers) to create a more robust and higher-bandwidth connection. It estimates the bandwidth volume (BWV) of each link and intelligently selects the best performing link for data transmission, dynamically reducing the BWV of the chosen link to optimize performance. This is crucial for handling the high bandwidth demands of telemedicine services like high-definition video.
  • Overlay Network for Telemedicine System (ONTMS): This creates a virtual overlay network on top of existing physical networks. It uses a self-discovery, self-organizing approach with relay nodes to ensure optimal and intelligent routing. This layer is designed to provide stable and reliable data transmission, even across long distances and diverse network conditions.
  • Non-intervention Remote Control: This method allows for the control of medical IoT devices and systems without requiring direct integration with their specific protocols. It achieves this by capturing the screen output of the target device and simulating control inputs (like keyboard and mouse commands) from the remote end. This simplifies implementation and enhances security.

The system architecture follows a layered approach: Terminal Layer (devices), Network Layer (physical and virtual networks), Platform Layer (services), and Application Layer (telemedicine services).

Datasets

The paper does not explicitly mention the use of pre-existing datasets for training machine learning models. Instead, it focuses on the deployment and evaluation of their novel telemedicine system.

The evaluation involved:

  • Network Performance Monitoring: Data was collected on bandwidth, delay, and packet loss ratio (PLR) from the access network and the overlay network during actual telemedicine sessions.
  • User Satisfaction Questionnaires: A questionnaire, adapted from existing validated instruments, was administered to 1988 participants (1920 patients and 68 doctors) to assess their experience with the system.

Key Insights and Ideas

  • Multinetwork Aggregation is Key: Combining multiple network connections (even consumer-grade 4G) significantly outperforms a single, best-performing network for telemedicine, especially in terms of delay and packet loss. This is a practical solution for improving network robustness without relying on expensive dedicated lines.
  • Overlay Networks Simplify Complexity: The ONTMS provides a unified and stable platform for diverse telemedicine services, abstracting away the complexities of underlying physical networks. This makes deployment and management more straightforward.
  • Non-Intrusive Remote Control is Practical: The screen capture and command simulation approach for remote control is a clever way to enable interaction with a wide range of medical devices without complex integration, making the system more versatile.
  • User Experience is Paramount: High user satisfaction scores across various aspects (fluency, convenience, perceived quality) demonstrate that the technical innovations translate into tangible benefits for both patients and clinicians.

Key Results

  • Access Network Performance: Aggregating Unicom 4G, Telecom 4G, and China Mobile 4G achieved significantly superior results compared to any single network. With an 8 Mbps detection bandwidth, the aggregated uplink bandwidth reached 7.93 Mbps, with a delay of 58.80 ms and a PLR of 0.06%, a stark improvement over China Mobile 4G's 4.09 Mbps bandwidth, 276.20 ms delay, and 45.38% PLR.
  • Overlay Network Performance: The mean round-trip delay from Beijing to Sanya (nearly 3000 km) via the ONTMS was 76 ms, with a PLR of 0 for the majority of the time.
  • User Satisfaction: Over 97% of participants found audio/video transmission and remote control to be fluent and convenient. 96% of patients rated the services with scores of 4 or 5. Notably, 92% of patients felt their telemedicine sessions were as good as face-to-face visits, and 94% would choose telemedicine again.

Limitations and Future Work

The authors acknowledge several limitations:

  • Limited Hospital Scope: The study primarily involved patients from 301 hospitals. Further research is needed to confirm if these findings generalize to other hospital types and regions.
  • Doctor Sample Size: The number of doctors included in the study was relatively small. Future work should incorporate a larger and more diverse group of medical professionals.
  • COVID-19 Context: The study was conducted during the COVID-19 pandemic. The system's performance and effectiveness in a non-epidemic period require further investigation.

Future work could involve extending the system to mobile applications and exploring its application in more specialized scenarios.

Summary updated

Abstract

In China, several problems were common in the telemedicine systems, such as the poor network stability and difficult interconnection. A new telemedicine system jointly driven by multinetwork integration and remote control has been designed to address these problems. A multilink aggregation algorithm and an overlay network for telemedicine system (ONTMS) were developed to improve network stability, and a non-intervention remote control method was designed for Internet of Things (IoT) devices/systems. The authors monitored the network parameters, and distributed the questionnaire to participants, for evaluating the telemedicine system and services. Under a detection bandwidth of 8 Mbps, the aggregation parameters of Unicom 4G, Telecom 4G, and China Mobile 4G were optimal, with an uplink bandwidth, delay, and packet loss ratio (PLR) of 7.93 Mbps, 58.80 ms, and 0.06%, respectively. These parameters were significantly superior to those of China Mobile 4G, the best single network (<i>p</i> < 0.001). Through the ONTMS, the mean round-trip transporting delay from Beijing to Sanya was 76 ms, and the PLR was 0 at vast majority of time. A total of 1988 participants, including 1920 patients and 68 doctors, completed the questionnaires. More than 97% of participants felt that the audio and video transmission and remote control were fluent and convenient. 96% of patients rated the telemedicine services with scores of 4 or 5. This system has shown robust network property and excellent interaction ability, and satisfied the needs of patients and doctors.
BibTeX
@inproceedings{wang2023design,
  author = {Ruiqing Wang and Jie Zhang and Shilin He and Huayuan Guo and Li Tao and Qin Zhong and Jun Ma and Jie Xu and Kunlun He},
  title = {{Design and application of a novel telemedicine system jointly driven by multinetwork integration and remote control: Practical experience from PLAGH, China}},
  booktitle = {Healthcare},
  year = {2023},
  doi = {10.1049/htl2.12057},
}
Figure