Comparison of Ocular Biomechanical Machine Learning Classifiers for Glaucoma Diagnosis

Application of machine learning methodology on patient functional and structural data has been shown to improve glaucoma classification accuracy. Intraocular pressure (IOP) and the biomechanical behaviors of the eye are early indicators of glaucoma. Four classifiers: linear logistic regression, support vector machine, random forest classifier and gradient boosting classifier are tested for discrimination using a 52-patient biomechanical data set that includes 20 glaucoma (40 eyes) and 32 healthy subjects (64 eyes). Results show that the 98.3% accuracy from linear logistic regression (LLR) is the highest correlation accuracy amongst the tested methods. The LLR classification accuracy is comparable with classification accuracies attained for classification using functional and structural measurements from image data sets. Since IOP elevation and biomechanical changes often precede imageable symptoms, the new biomechanics diagnostic classifier maybe used as a detection method for early stage glaucoma.

[1]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[2]  Nello Cristianini,et al.  Support vector machine classification and validation of cancer tissue samples using microarray expression data , 2000, Bioinform..

[3]  Jun Liu,et al.  Corneal stiffness affects IOP elevation during rapid volume change in the eye. , 2009, Investigative ophthalmology & visual science.

[4]  A. Hendrickson,et al.  Effect of intraocular pressure on rapid axoplasmic transport in monkey optic nerve. , 1974, Investigative ophthalmology.

[5]  C. Kaufmann,et al.  Intraocular pressure measurements using dynamic contour tonometry after laser in situ keratomileusis. , 2003, Investigative ophthalmology & visual science.

[6]  R. T. Hart,et al.  The optic nerve head as a biomechanical structure: a new paradigm for understanding the role of IOP-related stress and strain in the pathophysiology of glaucomatous optic nerve head damage , 2005, Progress in Retinal and Eye Research.

[7]  S. Lemeshow,et al.  A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study. , 1993, JAMA.

[8]  Ian A Sigal,et al.  Modeling individual-specific human optic nerve head biomechanics. Part I: IOP-induced deformations and influence of geometry , 2009, Biomechanics and modeling in mechanobiology.

[9]  Jun Liu,et al.  Influence of corneal biomechanical properties on intraocular pressure measurement: Quantitative analysis , 2005, Journal of cataract and refractive surgery.

[10]  Robert N Weinreb,et al.  Risk assessment in the management of patients with ocular hypertension. , 2004, American journal of ophthalmology.

[11]  A. Elsheikh,et al.  Assessment of Corneal Biomechanical Properties and Their Variation with Age , 2007, Current eye research.

[12]  W. Copes,et al.  Evaluating trauma care: the TRISS method. Trauma Score and the Injury Severity Score. , 1987, The Journal of trauma.

[13]  C. Glymour,et al.  Optical coherence tomography machine learning classifiers for glaucoma detection: a preliminary study. , 2005, Investigative ophthalmology & visual science.

[14]  Anders Heijl,et al.  Machine learning classifiers for glaucoma diagnosis based on classification of retinal nerve fibre layer thickness parameters measured by Stratus OCT , 2010, Acta ophthalmologica.

[15]  Robert N Weinreb,et al.  Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry. , 2002, Investigative ophthalmology & visual science.

[16]  David C C Lam,et al.  Individual-specific tonometry on porcine eyes. , 2014, Medical engineering & physics.

[17]  G. Papastergiou,et al.  Assessment of the Pascal dynamic contour tonometer in monitoring intraocular pressure in unoperated eyes and eyes after LASIK , 2004, Journal of cataract and refractive surgery.

[18]  Te-Won Lee,et al.  Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and glaucomatous eyes. , 2008, Investigative ophthalmology & visual science.

[19]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[20]  C. Sprung,et al.  Multiple organ dysfunction score: a reliable descriptor of a complex clinical outcome. , 1995, Critical care medicine.

[21]  C. R. Ethier,et al.  Factors influencing optic nerve head biomechanics. , 2005, Investigative ophthalmology & visual science.

[22]  David C C Lam,et al.  Characterization of corneal tangent modulus in vivo , 2013, Acta ophthalmologica.

[23]  A. Tuulonen,et al.  Nerve fiber layer defects with normal visual fields. Do normal optic disc and normal visual field indicate absence of glaucomatous abnormality? , 1993, Ophthalmology.

[24]  Ian A Sigal,et al.  Modeling individual-specific human optic nerve head biomechanics. Part II: influence of material properties , 2009, Biomechanics and modeling in mechanobiology.

[25]  David C C Lam,et al.  Partial contact indentation tonometry for measurement of corneal properties-independent intraocular pressure. , 2012, Molecular & cellular biomechanics : MCB.

[26]  Tarek Mekhail,et al.  Diagnosis of lung cancer by the analysis of exhaled breath with a colorimetric sensor array , 2007, Thorax.

[27]  I. Sayek,et al.  Validation of MPI and PIA II in two different groups of patients with secondary peritonitis. , 2001, Hepato-gastroenterology.

[28]  David C C Lam,et al.  Comparative study of corneal tangent elastic modulus measurement using corneal indentation device. , 2014, Medical engineering & physics.

[29]  A. Sommer,et al.  Relationship between intraocular pressure and primary open angle glaucoma among white and black Americans. The Baltimore Eye Survey. , 1991, Archives of ophthalmology.

[30]  A. Sommer,et al.  The nerve fiber layer in the diagnosis of glaucoma. , 1977, Archives of ophthalmology.

[31]  J Katz,et al.  Risk factors for the development of glaucomatous visual field loss in ocular hypertension. , 1994, Archives of ophthalmology.

[32]  E. Jaurrieta,et al.  Prognostic factors for mortality in left colonic peritonitis: a new scoring system. , 2000, Journal of the American College of Surgeons.

[33]  David C C Lam,et al.  Effect of age-stiffening tissues and intraocular pressure on optic nerve damages. , 2012, Molecular & cellular biomechanics : MCB.