Abstract
Purpose
Return zone depth (RZD) and landing zone angle (LZA) are important parameters of corneal
refractive therapy (CRT) lenses. A new machine learning algorithm is proposed for
prescribing CRT lens parameters in Chinese adolescents with myopia.
Methods
This is a retrospective study. In total, 1037 Chinese adolescents with myopia (1037
right eyes) were enrolled. A calculation model based on corneal elevation maps was
constructed to calculate RZD and LZA for the four quadrants. Furthermore, multiple
linear regression and optimized machine learning models were established to predict
RZD and LZA values for different combinations of age, sex, and ocular parameters.
The four methods (sliding card, linear regression, calculation and optimized machine
learning) were then compared to the parameters of the final ordered lens.
Results
The optimized machine learning pipeline achieved the best performance. Age, sex, horizontal
visible iris diameter (HVID), spherical equivalent refraction degree (SER), eccentricity
(e), keratometric (K) readings, corneal astigmatism (CA), axial length (AL), AL/corneal
curvature ratio (AL/MK), and anterior chamber depth (ACD) were significant to the
machine learning model. The R values for the nasal, temporal, superior and inferior
LZA based on machine learning were 0.843, 0.693, 0.866 and 0.762, respectively, and
those for the RZD were 0.970, 0.964, 0.975 and 0.964, respectively.
Conclusions
The feasibility and efficiency of an optimized machine learning method to predict
LZA and RZD parameters has been demonstrated. The advantage of the proposed method
is that it is more accurate, easier to use and faster to implement than the traditional
sliding card method.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Contact Lens and Anterior EyeAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Myopia: an epidemic of possibilities?.Optom Vis Sci. 2015; 35: 349-351
- The epidemics of myopia: aetiology and prevention.Prog Retin Eye Res. 2018; 62: 134-149
- Refractive errors in an elderly chinese population in Taiwan: the shihpai eye study.Invest Ophthalmol Vis Sci. 2003; 44: 4630
- The myopia boom.Nature. 2015; 519: 276-278
- Myopia control using toric orthokeratology (TO-SEE study).Invest Ophthalmol Vis Sci. 2013; 54: 6510-6517
- Orthokeratology to control myopia progression: a meta-analysis.PLoS One. 2015; 10e0130646
- Long-term effect of overnight orthokeratology on axial length elongation in childhood myopia: a 5-year follow-up study.Invest Ophthalmol Vis Sci. 2012; 53: 3913-3919
- Overnight orthokeratology - response.Optom Vis Sci. 2000; 77: 252-259
- Orthokeratology review and update.Clin Exp Optom. 2010; 89: 124-143
- Corneal modeling.Cornea. 1988; 7: 30-35
- Nomogram, corneal topography, and final prescription relations for corneal refractive therapy.Optom Vis Sci. 2007; 84: 59-64
- Design variables and fitting philosophies of reverse geometry lenses, Orthokeratology: principles and Practice.1st ed. Elsevier, Butterworth-Heinemann2004: 89-91
- Comparative evaluation of Asian and white ocular topography.Optom Vis Sci. 2014; 91: 1396
- Use of a support vector machine for keratoconus and subclinical keratoconus detection by topographic and tomographic data.Ophthalmology. 2012; 119: 2231-2238
- Automated decision tree classification of corneal shape.Optom Vis Sci. 2005; 82: 1038-1046
- Machine learning for medical imaging.Radiographics. 2017; 37160130
- The relationship between corneal biomechanics and anterior segment parameters in the early stage of orthokeratology.Medicine. 2017; 96: e6907
- A novel fitting algorithm for alignment curve radius estimation using corneal elevation data in orthokeratology lens trial.Contact Lens Anterior Eye. 2017; 40: 401-407
- Estimating the error rate of a prediction rule : improvement on cross-validation.J Am Stat Assoc. 1983; 78: 316-331
- A study on SMO-type decomposition methods for support vector machines.IEEE T Neural Networ. 2006; 17: 893-908
- “Gaussian processes for machine learning”.Int J Neural Syst. 2004; 14: 69-106
- Robust regression using iteratively reweighted least-squares.Commun Stat-Theor M. 1977; 6: 813-827
- An empirical comparison of pattern recognition, neural nets, and machine learning classification methods.Proc. of Ijcai. 1989; 89
- Efficacy, safety and acceptability of orthokeratology on slowing axial elongation in myopic children by meta-analysis.Curr Eye Res. 2016; 41: 600
- Overnight orthokeratology lens wear can inhibit the central stromal edema response.Invest Ophthalmol Vis Sci. 2005; 46: 2334-2340
- Efficacy comparison of 16 interventions for myopia control in children: a network meta-analysis.Ophthalmology. 2016; 123: 697-708
- Variation in normal corneal shape and the influence of eyelid morphometry.Optom Vis Sci. 2015; 92: 286
- Corneal stiffness and its relationship with other corneal biomechanical and nonbiomechanical parameters in myopic eyes of chinese patients.Cornea. 2018; 37: 1
- Predictive role of corneal Q-value differences between nasal-temporal and superior-inferior quadrants in orthokeratology lens decentration.Medicine. 2017; 96: e5837
- Prediction of orthokeratology Lens decentration with corneal elevation.Optom Vis Sci. 2017; 94: 903
- Introduction to machine learning for ophthalmologists.Semin Ophthalmol. 2018; : 1-23
- Artificial intelligence and deep learning in ophthalmology.Br J Ophthalmol. 2019; 103: 167-175
- Current state and future prospects of artificial intelligence in ophthalmology: a review.Graefes Arch Clin Exp Ophthalmol. 2019; 47: 128-139
- Deep learning in ophthalmology: the technical and clinical considerations.Prog Retin Eye Res. 2019; 72100759
- Comparison and repeatability of keratometric and corneal power measurements obtained by Orbscan II, Pentacam, and Galilei corneal tomography systems.Am J Ophthalmol. 2013; 156: 53-60
- Comparison of Pentacam and Orbscan IIz on posterior curvature topography measurements in keratoconus eyes.Ophthalmology. 2006; 113: 1629-1632
Article info
Publication history
Published online: May 14, 2020
Accepted:
May 3,
2020
Received in revised form:
April 26,
2020
Received:
March 12,
2020
Identification
Copyright
© 2020 British Contact Lens Association. Published by Elsevier Ltd. All rights reserved.
