|
Getting your Trinity Audio player ready...
|
In the fight against COVID-19, contact tracing is crucial, but current methods still need to be improved. It is found that manual tracing is slow and inaccurate, and smartphone tracing has low adoption due to privacy concerns, especially among healthcare workers at high infection risk. To tackle these issues, researchers led by Chenyang Lu, the Fullgraf Professor at the McKelvey School of Engineering and director of the AI for Health Institute at Washington University in St. Louis and an expert in cyber-physical systems, have created Contact Tracing for Hospitals (CATCH), an automated hospital-specific contact tracing system.
Jingwen Zhang said that based on conversations with healthcare professionals, the researchers have identified the need to tailor contact tracing methods to different room types based on their unique characteristics and staff working patterns.
“For example, within the ICU, morning rounds involving collaborative discussions among healthcare workers in the hallway represent a significant hotspot for close contacts, often lasting several hours. To address this scenario, our contact tracing system integrated a specialised clustering method designed to identify the members of the patient round team accurately.”
By customising CATCH to align with the environmental characteristics and behaviours of healthcare workers in distinct ICU areas, the team created a more precise and efficient system for pinpointing close contacts. CATCH employs a range of innovative contact tracing algorithms tailored to each situation, enabling it to adapt to the intricate dynamics of a hospital setting and achieve superior accuracy compared to existing methods.
The team assessed CATCH within the COVID-19 ICU at Barnes-Jewish Hospital. Impressively, it consistently outperformed other contact tracing methods, demonstrating superior accuracy, heightened effectiveness, and remarkable efficiency.
Maria Cristina Vazquez Guillamet, MD, an associate professor of medicine in the Division of Infectious Diseases at Washington University School of Medicine, shed light on the system’s performance during simulations involving positive cases. She noted that the CATCH system displayed an additional contact discovery rate of 15%, leading to a substantial reduction in the effective reproduction number, a crucial indicator of viral spread, by more than 50%. This outstanding outcome effectively curbs virus transmission among healthcare workers.
One of the aspects of CATCH is its scalability and adaptability, rendering it well-suited for deployment in various outbreaks. The system’s parameter settings can be customised to accommodate the specific characteristics of different pathogens, making it a versatile tool for addressing future pandemics.
Through its rapid and accurate identification of potential COVID-19 exposures, delivering a comprehensive list of contacts in just 20 minutes, CATCH effectively mitigates the risk of virus transmission within hospital units, ultimately preserving lives.
In the future, researchers anticipate a continuously evolving landscape of infectious diseases, each presenting unique challenges. CATCH is well-positioned to remain an invaluable resource in this dynamic environment. Its adaptability allows healthcare workers to address not only the specific criteria of the present but also to respond flexibly to the changing characteristics of future pathogens.
It is crucial to maintain a proactive stance in pandemic preparedness, and CATCH exemplifies this by serving as a versatile tool that can be seamlessly tailored to emerging health crises. The lessons learned and insights gained from its application during the COVID-19 pandemic will inform and guide the approach to future challenges in infectious diseases.
