Normal tension glaucoma (NTG) is a chronic progressive optic neuropathy characterized by optic nerve damage despite normal intraocular pressure. This indicates that, in addition to intraocular pressure, hemodynamic and biomechanical factors play an important role in disease pathogenesis. Despite scientific progress, clinical practice still lacks methods that enable individualized assessment of these dynamic processes in specific patients.
The aim of this project is to perform a retrospective analysis of accumulated clinical and instrumental data and to develop a personalized NTG risk assessment tool using numerical modeling and artificial intelligence methods. Dynamic parameters of ocular pulse waves and optical coherence tomography (OCT) images will be analyzed to identify characteristic features and markers associated with NTG.
The analysis will use previously collected data obtained with the non-invasive intracranial pulse wave monitoring system “Archimedes 02”. Previous studies have shown that the amplitude of ocular pulse waves in NTG patients is nearly twice as high as in healthy individuals; however, the mechanisms underlying this difference remain unclear. The project will investigate relationships between pulse wave dynamics and structural and functional ocular changes at the individual level.
An integrated computational model will be developed in which patients’ clinical data (OCT markers and pulse wave parameters) will be transformed into a virtual eye model enabling simulation of disease progression. Algorithms based on differential and integral equations will model hemodynamic and biomechanical processes and predict disease progression. Machine learning methods will also be applied to identify relationships between pulse wave parameters and ocular changes.
The final outcome will be tools for NTG analysis and progression risk assessment, supporting more accurate evaluation of disease course and personalized monitoring and treatment strategies.
Project funding:
KTU fund for internal investment
Period of project implementation: 2026-04-01 - 2026-12-31
Project partners: Lithuanian University of Health Sciences, Lithuanian Energy Institute
