Digital twin for ocular hemodynamics: Combining physiology-based modeling and machine learning for personalized...

Area of Science:

• Ophthalmology
• Biomedical Engineering
• Computational Physiology

Background:

• Glaucoma is a leading cause of irreversible blindness.
• Retinal hemodynamics are influenced by both intraocular pressure (IOP) and systemic blood pressure (BP).
• Understanding the interplay between IOP, BP, and ocular blood flow is crucial for glaucoma management.

Purpose of the Study:

• To investigate the combined effects of IOP and BP on retinal hemodynamics and glaucoma progression.
• To develop and apply a novel physiology-based digital twin for ocular hemodynamics (DT-OH).
• To identify hemodynamic profiles associated with glaucoma progression risk.

Main Methods:

• Developed a digital twin for ocular hemodynamics (DT-OH) integrating mathematical modeling and machine learning.
• Simulated retinal blood flow dynamics using individualized IOP and BP data.
• Applied the DT-OH to clinical data from the Indianapolis Glaucoma Progression Study (IGPS).

Main Results:

• The DT-OH identified three distinct hemodynamic profiles based on combined IOP and BP.
• One specific baseline hemodynamic profile was significantly associated with a higher risk of glaucoma progression.
• These profiles reflect unique ocular blood flow regulation patterns.

Conclusions:

• The DT-OH provides physiological insights into the interplay of systemic and ocular factors in glaucoma.
• Findings enhance understanding of glaucoma pathophysiology.
• Supports the development of personalized risk assessment tools for glaucoma incorporating both IOP and BP.