Accurate intraocular pressure prediction from applanation response data using genetic algorithm and neural networks

Jamshid Ghaboussi, Tae Hyun Kwon, David A. Pecknold, Youssef M.A. Hashash

Research output: Contribution to journalArticlepeer-review

Abstract

The fact that Goldmann applanation tonometry does not accurately account for individual corneal elastic stiffness often leads to inaccuracy in the measurement of intraocular pressure (IOP). IOP should account not only for the effect of central corneal thickness (CCT) but should also account for other corneal biomechanical factors. A computational method for accurate and reliable determination of IOP is investigated with a modified applanation tonometer in this paper. The proposed method uses a combined genetic algorithm/neural network procedure to match the clinically measured applanation force-displacement history with that obtained from a nonlinear finite element simulation of applanation. An additional advantage of the proposed method is that it also provides the ability to determine CCT and material properties of the cornea from the same applanation response data. The performance of the proposed method has been demonstrated through a parametric study and via comparison with a well known clinical case. The proposed method is also shown to be computationally efficient, which is an important practical consideration for clinical application.

Original languageEnglish (US)
Pages (from-to)2301-2306
Number of pages6
JournalJournal of Biomechanics
Volume42
Issue number14
DOIs
StatePublished - Oct 16 2009

Keywords

  • Central corneal thickness
  • Cornea
  • Finite element simulation
  • Genetic algorithm
  • Goldmann applanation tonometry
  • Intraocular pressure
  • Neural networks

ASJC Scopus subject areas

  • Biophysics
  • Orthopedics and Sports Medicine
  • Biomedical Engineering
  • Rehabilitation

Fingerprint Dive into the research topics of 'Accurate intraocular pressure prediction from applanation response data using genetic algorithm and neural networks'. Together they form a unique fingerprint.

Cite this