Smart contact lens-trained digital twin for device-free personalized uric acid prediction

Area of Science:

• Biomedical Engineering
• Ophthalmology
• Metabolic Health

Background:

• Tears are a source of biomarkers for noninvasive disease monitoring.
• Correlation between serum uric acid (SUA) and tear uric acid (TUA) is not well-established, limiting clinical use.
• Current uric acid testing relies on invasive blood draws.

Purpose of the Study:

• To develop and validate a wireless smart contact lens for real-time, noninvasive tear uric acid (TUA) monitoring.
• To establish a correlation between TUA and serum uric acid (SUA).
• To create a digital twin framework for predicting uric acid dynamics and personalized metabolic health monitoring.

Main Methods:

• Development of a wireless smart contact lens for TUA detection.
• Correlation analysis in animal models (rabbits) and human participants (including hyperuricemia and gout patients).
• Development of a regression model linking TUA to SUA and construction of lifestyle-informed digital twins.

Main Results:

• The smart contact lens successfully monitored TUA in real-time and noninvasively.
• A strong linear relationship was found between TUA and SUA.
• Personalized TUA fluctuation profiles were characterized in response to diet and activity.
• A regression model accurately estimated SUA from TUA.
• Digital twins predicted daily uric acid dynamics, enabling device-free monitoring.

Conclusions:

• The smart contact lens provides a viable, noninvasive alternative to blood-based uric acid testing.
• The device and digital twin framework facilitate personalized metabolic health monitoring and disease management, particularly for conditions like gout.
• This technology offers a practical approach to unobtrusive, continuous health surveillance.