The Evonik-Mainz Eye Care-Study (EMECS): Development of an Expert System for Glaucoma Risk Detection in a Working...

Area of Science:

• Ophthalmology
• Medical Imaging
• Public Health

Background:

• Glaucoma screening in occupational settings is crucial for early detection.
• Existing screening methods may have limitations in accuracy and efficiency.
• An expert system offers a potential solution for systematic glaucoma detection.

Purpose of the Study:

• To develop and validate an expert system for glaucoma screening in a working population.
• To integrate optic nerve head (ONH) imaging, frequency doubling technology (FDT) visual field testing, and intraocular pressure (IOP) measurements.
• To establish a reliable screening model based on human expert procedures.

Main Methods:

• A cohort of 13,037 employees aged 40-65 underwent screening.
• An experienced glaucoma specialist established a "gold standard" classification.
• A novel screening model incorporating ONH assessment, IOP, and FDT data was developed and tested against the gold standard.

Main Results:

• The expert system achieved a sensitivity of 83.8% and a specificity of 99.6% for identifying glaucoma suspects.
• The positive predictive value was 80.2%, and the negative predictive value was 99.6%.
• Simple screening models based solely on IOP or FDT showed inadequate diagnostic accuracy.

Conclusions:

• The developed expert system demonstrates satisfactory diagnostic accuracy for glaucoma screening in a working population.
• The model's effectiveness is attributed to the integration of ONH, IOP, and FDT parameters.
• Further validation by different experts across diverse populations is recommended.