Automated Elicitation of Human and Ecological Health Indicators: An LLM-Based Practical Implementation for One...

Area of Science:

• Environmental Health
• Digital Health
• One Health

Background:

• Urban freshwater ecosystems face complex health challenges impacting both wildlife and human populations.
• Effective monitoring requires integrating diverse data streams and analytical approaches.
• The One Health framework emphasizes the interconnectedness of human, animal, and environmental health.

Purpose of the Study:

• To develop an automated method for identifying human and ecological health indicators in urban freshwater environments.
• To leverage the One Digital Health framework, integrating One Health and Digital Health principles.
• To support the OneAquaHealth project by enhancing environmental monitoring and health surveillance.

Main Methods:

• A systematic literature review was conducted focusing on urban freshwater environments.
• Large Language Models (LLMs) were primarily employed for automated text analysis and information extraction.
• The study focused on identifying key health indicators relevant to aquatic ecosystems and human well-being.

Main Results:

• An automated method for identifying human and ecological health indicators was successfully developed.
• The application of LLMs streamlined the literature review and data extraction process.
• Key indicators linking urban aquatic health to human wellness were identified.

Conclusions:

• Automated identification using LLMs within the One Digital Health framework is effective for monitoring urban freshwater health.
• The findings provide a foundation for enhanced environmental monitoring and integrated health approaches.
• This work advances the goals of the OneAquaHealth project by digitizing and connecting health information across domains.