Machine learning based strategy surpasses the traditional method for selecting the first trial Lens parameters for corneal refractive therapy in Chinese adolescents with myopia

  • Author Footnotes
    1 These two authors contributed equally.
    Yuzhuo Fan
    Footnotes
    1 These two authors contributed equally.
    Affiliations
    Department of Ophthalmology & Clinical Center of Optometry, Peking University People’s Hospital, Beijing 100044, China

    College of Optometry, Peking University Health Science Center, Beijing, China

    Eye Disease and Optometry Institute, Peking University People’s Hospital, China

    Beijing Key Laboratory of Diagnosis and Therapy of Retinal and Choroid Diseases, China
    Search for articles by this author
  • Author Footnotes
    1 These two authors contributed equally.
    Zekuan Yu
    Footnotes
    1 These two authors contributed equally.
    Affiliations
    Academy for Engineering & Technology, Fudan University, China

    Department of Biomedical Engineering, College of Engineering, Peking University, Beijing 100871, China
    Search for articles by this author
  • Zisu Peng
    Affiliations
    Department of Ophthalmology & Clinical Center of Optometry, Peking University People’s Hospital, Beijing 100044, China

    College of Optometry, Peking University Health Science Center, Beijing, China

    Eye Disease and Optometry Institute, Peking University People’s Hospital, China

    Beijing Key Laboratory of Diagnosis and Therapy of Retinal and Choroid Diseases, China
    Search for articles by this author
  • Qiong Xu
    Affiliations
    Department of Ophthalmology & Clinical Center of Optometry, Peking University People’s Hospital, Beijing 100044, China

    College of Optometry, Peking University Health Science Center, Beijing, China

    Eye Disease and Optometry Institute, Peking University People’s Hospital, China

    Beijing Key Laboratory of Diagnosis and Therapy of Retinal and Choroid Diseases, China
    Search for articles by this author
  • Tao Tang
    Affiliations
    Department of Ophthalmology & Clinical Center of Optometry, Peking University People’s Hospital, Beijing 100044, China

    College of Optometry, Peking University Health Science Center, Beijing, China

    Eye Disease and Optometry Institute, Peking University People’s Hospital, China

    Beijing Key Laboratory of Diagnosis and Therapy of Retinal and Choroid Diseases, China
    Search for articles by this author
  • Kai Wang
    Correspondence
    Corresponding author at: Department of Ophthalmology & Clinical Center of Optometry, Peking University People’s Hospital, Beijing 100044, China.
    Affiliations
    Department of Ophthalmology & Clinical Center of Optometry, Peking University People’s Hospital, Beijing 100044, China

    College of Optometry, Peking University Health Science Center, Beijing, China

    Eye Disease and Optometry Institute, Peking University People’s Hospital, China

    Beijing Key Laboratory of Diagnosis and Therapy of Retinal and Choroid Diseases, China
    Search for articles by this author
  • Qiushi Ren
    Affiliations
    Department of Biomedical Engineering, College of Engineering, Peking University, Beijing 100871, China
    Search for articles by this author
  • Mingwei Zhao
    Affiliations
    Department of Ophthalmology & Clinical Center of Optometry, Peking University People’s Hospital, Beijing 100044, China

    College of Optometry, Peking University Health Science Center, Beijing, China

    Eye Disease and Optometry Institute, Peking University People’s Hospital, China

    Beijing Key Laboratory of Diagnosis and Therapy of Retinal and Choroid Diseases, China
    Search for articles by this author
  • Jia Qu
    Affiliations
    College of Optometry, Peking University Health Science Center, Beijing, China

    School of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, China
    Search for articles by this author
  • Author Footnotes
    1 These two authors contributed equally.

      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 and Personal
      One-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 Eye
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Mutti D.O.
        • Bullimore M.A.
        Myopia: an epidemic of possibilities?.
        Optom Vis Sci. 2015; 35: 349-351
        • Morgan I.G.
        • French A.N.
        • Ashby R.S.
        • Guo X.
        • Ding X.
        • He M.
        • et al.
        The epidemics of myopia: aetiology and prevention.
        Prog Retin Eye Res. 2018; 62: 134-149
        • Ching-Yu C.
        • Wen-Ming H.
        • Jorn-Hon L.
        • Su-Ying T.
        • Pesus C.
        Refractive errors in an elderly chinese population in Taiwan: the shihpai eye study.
        Invest Ophthalmol Vis Sci. 2003; 44: 4630
        • Dolgin E.
        The myopia boom.
        Nature. 2015; 519: 276-278
        • Connie C.
        • Sin Wan C.
        • Pauline C.
        Myopia control using toric orthokeratology (TO-SEE study).
        Invest Ophthalmol Vis Sci. 2013; 54: 6510-6517
        • Yuan S.
        • Fan X.
        • Ting Z.
        • Manli L.
        • Danyang W.
        • Yile C.
        • et al.
        Orthokeratology to control myopia progression: a meta-analysis.
        PLoS One. 2015; 10e0130646
        • Takahiro H.
        • Tetsuhiko K.
        • Fumiki O.
        • Hideto T.
        • Tetsuro O.
        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
        • Nichols J.J.
        • Marsich M.M.
        • Nguyen M.
        • Barr J.T.
        • Bullimore M.A.
        Overnight orthokeratology - response.
        Optom Vis Sci. 2000; 77: 252-259
        • Swarbrick H.A.
        Orthokeratology review and update.
        Clin Exp Optom. 2010; 89: 124-143
        • Gormley D.J.
        • Gersten M.
        • Koplin R.S.
        • Lubkin V.
        Corneal modeling.
        Cornea. 1988; 7: 30-35
        • Gonzalez-Meijome J.
        • Villa-Collar C.
        Nomogram, corneal topography, and final prescription relations for corneal refractive therapy.
        Optom Vis Sci. 2007; 84: 59-64
        • Mountford J.
        • Ruston D.
        • Dave T.
        Design variables and fitting philosophies of reverse geometry lenses, Orthokeratology: principles and Practice.
        1st ed. Elsevier, Butterworth-Heinemann2004: 89-91
        • Sheila H.C.
        • Brennan N.A.
        • Yoshi I.
        • Graeme Y.
        Comparative evaluation of Asian and white ocular topography.
        Optom Vis Sci. 2014; 91: 1396
        • Arbelaez M.Clara
        • Versaci Francesco
        • Vestri Gabriele
        • et al.
        Use of a support vector machine for keratoconus and subclinical keratoconus detection by topographic and tomographic data.
        Ophthalmology. 2012; 119: 2231-2238
        • Twa M.D.
        • Parthasarathy S.
        • Roberts C.
        • Mahmoud A.M.
        • Raasch T.W.
        • Bullimore M.A.
        Automated decision tree classification of corneal shape.
        Optom Vis Sci. 2005; 82: 1038-1046
        • Erickson B.J.
        • Korfiatis P.
        • Akkus Z.
        • Kline T.L.
        Machine learning for medical imaging.
        Radiographics. 2017; 37160130
        • Chen R.
        • Mao X.
        • Jiang J.
        • Shen M.
        • Lian Y.
        • Zhang B.
        • et al.
        The relationship between corneal biomechanics and anterior segment parameters in the early stage of orthokeratology.
        Medicine. 2017; 96: e6907
        • Zhang L.
        • Zhang Y.
        • Liu Y.
        • Wang K.
        • Zhao M.
        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
        • Efron B.
        Estimating the error rate of a prediction rule : improvement on cross-validation.
        J Am Stat Assoc. 1983; 78: 316-331
        • Pai-Hsuen C.
        • Rong-En F.
        • Chih-Jen L.
        A study on SMO-type decomposition methods for support vector machines.
        IEEE T Neural Networ. 2006; 17: 893-908
        • Seeger M.
        “Gaussian processes for machine learning”.
        Int J Neural Syst. 2004; 14: 69-106
        • Holland P.W.
        • Welsch R.E.
        Robust regression using iteratively reweighted least-squares.
        Commun Stat-Theor M. 1977; 6: 813-827
        • Weiss S.M.
        An empirical comparison of pattern recognition, neural nets, and machine learning classification methods.
        Proc. of Ijcai. 1989; 89
        • Li S.M.
        • Kang M.T.
        • Wu S.S.
        • Liu L.R.
        • Li H.
        • Chen Z.
        • et al.
        Efficacy, safety and acceptability of orthokeratology on slowing axial elongation in myopic children by meta-analysis.
        Curr Eye Res. 2016; 41: 600
        • Alharbi A.
        • Ha L.H.D.
        Overnight orthokeratology lens wear can inhibit the central stromal edema response.
        Invest Ophthalmol Vis Sci. 2005; 46: 2334-2340
        • Huang J.
        • Wen D.
        • Wang Q.
        • Mcalinden C.
        • Flitcroft I.
        • Chen H.
        • et al.
        Efficacy comparison of 16 interventions for myopia control in children: a network meta-analysis.
        Ophthalmology. 2016; 123: 697-708
        • Vinod M.
        • Paul G.
        • Helen S.
        Variation in normal corneal shape and the influence of eyelid morphometry.
        Optom Vis Sci. 2015; 92: 286
        • Zhang Y.
        • Wang Y.
        • Li L.
        • Dou R.
        • Wu W.
        • Wu D.
        • et al.
        Corneal stiffness and its relationship with other corneal biomechanical and nonbiomechanical parameters in myopic eyes of chinese patients.
        Cornea. 2018; 37: 1
        • Li J.
        • Yang C.
        • Xie W.
        • Zhang G.
        • Li X.
        • Wang S.
        • et al.
        Predictive role of corneal Q-value differences between nasal-temporal and superior-inferior quadrants in orthokeratology lens decentration.
        Medicine. 2017; 96: e5837
        • Chen Z.
        • Xue F.
        • Zhou J.
        • Qu X.
        • Zhou X.
        Prediction of orthokeratology Lens decentration with corneal elevation.
        Optom Vis Sci. 2017; 94: 903
        • Consejo A.
        • Melcer T.
        • Rozema J.J.
        Introduction to machine learning for ophthalmologists.
        Semin Ophthalmol. 2018; : 1-23
        • Ting D.S.W.
        • Pasquale L.R.
        • Peng L.
        • Campbell J.P.
        • Lee A.Y.
        • Raman R.
        • et al.
        Artificial intelligence and deep learning in ophthalmology.
        Br J Ophthalmol. 2019; 103: 167-175
        • Hogarty D.T.
        • Mackey D.A.
        • Hewitt A.W.
        Current state and future prospects of artificial intelligence in ophthalmology: a review.
        Graefes Arch Clin Exp Ophthalmol. 2019; 47: 128-139
        • Ting D.S.W.
        • Peng L.
        • Varadarajan A.V.
        • Keane P.A.
        • Burlina P.M.
        • Chiang M.F.
        • et al.
        Deep learning in ophthalmology: the technical and clinical considerations.
        Prog Retin Eye Res. 2019; 72100759
        • Crawford A.Z.
        • Patel D.V.
        • Mcghee C.N.J.
        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
        • Quisling S.
        • Sjoberg S.
        • Zimmerman B.
        • Goins K.
        • Sutphin J.
        Comparison of Pentacam and Orbscan IIz on posterior curvature topography measurements in keratoconus eyes.
        Ophthalmology. 2006; 113: 1629-1632