Advertisement
Research Article| Volume 45, ISSUE 3, 101474, June 2022

Download started.

Ok

Machine learning algorithm improves accuracy of ortho-K lens fitting in vision shaping treatment

  • 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, Shanghai 200433, China

    Center for Shanghai Intelligent Imaging for Critical Brain Diseases Engineering & Technology Research, Huashan Hospital, Fudan University, Shanghai 200040, 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
  • Xiao Liu
    Affiliations
    Academy for Engineering & Technology, Fudan University, Shanghai 200433, China

    Center for Shanghai Intelligent Imaging for Critical Brain Diseases Engineering & Technology Research, Huashan Hospital, Fudan University, Shanghai 200040, 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
  • 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
  • Yan Li
    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. College of Optometry, Peking University Health Science Center, Beijing, 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
  • 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
  • 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
  • Author Footnotes
    1 These two authors contributed equally.

      Abstract

      Purpose

      To construct a machine learning (ML)-based model for estimating the alignment curve (AC) curvature in orthokeratology lens fitting for vision shaping treatment (VST), which can minimize the number of lens trials, improving efficiency while maintaining accuracy, with regards to its improvement over a previous calculation method.

      Methods

      Data were retrospectively collected from the clinical case files of 1271 myopic subjects (1271 right eyes). The AC curvatures calculated with a previously published algorithm were used as the target data sets. Four kinds of machine learning algorithms were implemented in the experimental analyses to predict the targeted AC curvatures: robust linear regression models, support vector machine (SVM) regression models with linear kernel functions, bagging decision trees, and Gaussian processes. The previously published calculation method and the novel machine learning method were then compared to assess the final parameters of ordered lenses.

      Results

      The linear SVM and Gaussian process machine learning models achieved the best performance. The input variables included sex, age, horizontal visible iris diameter (HVID), spherical refraction (SER), cylindrical refraction, eccentricity value (e value), flat K (K1) and steep K (K2) readings, anterior chamber depth (ACD), and axial length (AL). The R-squared values for the output AC1K1, AC1K2 and AC2K1 values were 0.91, 0.84, and 0.73, respectively. The previous calculation method and machine learning methods displayed excellent consistency, and the proposed methods performed best based on flat K reading and e values.

      Conclusions

      The ML model can provide practitioners with an efficient method for estimating the AC curvatures of VST lenses and reducing the probability of cross-infection originating from trial lenses, which is especially useful during pandemics, such as that for COVID-19.

      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 access
      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

        • Holden B.A.
        • Fricke T.R.
        • Wilson D.A.
        • Jong M.
        • Naidoo K.S.
        • Sankaridurg P.
        • et al.
        Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050.
        Ophthalmology. 2016; 123: 1036-1042
        • Zhao J.L.
        • Pan X.J.
        • Sui R.F.
        • Munoz S.R.
        • Ellwein L.B.
        Refractive error study in children: results from Shunyi District. China.
        Ophthalmology. 2000; 129: 427-435
        • He M.
        • Zeng J.
        • Liu Y.
        • Xu J.
        • Pokharel G.P.
        • Ellwein L.B.
        Refractive error and visual impairment in urban children in southern china.
        Invest Ophthalmol Vis Sci. 2004; 45: 793-799
        • Kleinstein R.N.
        • Jones L.A.
        • Hullett S.
        • Kwon S.
        • Lee R.J.
        • Friedman N.E.
        • et al.
        Refractive error and ethnicity in children.
        Arch Ophthalmol. 2003; 121: 1141
        • Li S.M.
        • Li S.Y.
        • Liu L.R.
        • Zhou Y.H.
        • Yang Z.
        • Kang M.T.
        • et al.
        Peripheral refraction in 7- and 14-year-old children in central China: the Anyang Childhood Eye Study.
        Br J Ophthalmol. 2015; 99: 674-679
        • Dolgin E.
        The myopia boom.
        Nature. 2015; 519: 276-278
        • Shamanna B.R.
        • Dandona L.
        • Rao G.N.
        Economic burden of blindness in India.
        Indian J Ophthalmol. 1998; 46: 169-172
        • Fricke T.R.
        • Holden B.A.
        • Wilson D.A.
        • Schlenther G.
        • Naidoo K.S.
        • Resnikoff S.
        • et al.
        Global cost of correcting vision impairment from uncorrected refractive error.
        Bull World Health Organ. 2012; 90: 728-738
        • Naidoo K.S.
        • Fricke T.R.
        • Frick K.D.
        • Jong M.
        • Naduvilath T.J.
        • Resnikoff S.
        • et al.
        Potential lost productivity resulting from the global burden of myopia.
        Ophthalmology. 2019; 126: 338-346
        • Wong T.Y.
        • Ferreira A.
        • Hughes R.
        • Carter G.
        • Mitchell P.
        Epidemiology and disease burden of pathologic myopia and myopic choroidal neovascularization: an evidence-based systematic review.
        Am J Ophthalmol. 2014; 157: 9-25.e12
        • Pascarella G.
        • Strumia A.
        • Piliego C.
        • Bruno F.
        • Agrò F.E.
        COVID-19 diagnosis and management: a comprehensive review.
        J Intern Med. 2020; : 192-206
        • Pellegrini M.
        • Bernabei F.
        • Scorcia V.
        • Giannaccare G.
        May home confinement during the COVID-19 outbreak worsen the global burden of myopia?.
        Graefes Arch Clin Exp Ophthalmol. 2020; 258: 2069-2070
        • Parmet W.E.
        • Sinha M.S.
        Covid-19 — The law and limits of quarantine.
        N Engl J Med. 2020; 382: e28
        • Wong C.W.
        • Tsai A.
        • Jonas J.B.
        • Ohno-Matsui K.
        • Ting D.S.W.
        Digital screen time during COVID-19 pandemic: risk for a further myopia boom?.
        Am J Ophthalmol. 2020; 223: 333-337
        • Cho P.
        • Cheung S.W.
        Retardation of myopia in orthokeratology (ROMIO) study: a 2-year randomized clinical trialretardation of myopia in orthokeratology study.
        Invest Ophthalmol Vis Sci. 2012; 53: 7077-7085
        • 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
        • Swarbrick H.A.
        Orthokeratology review and update.
        Clin Exp Optom. 2006; 89: 124-143
        • Li S.
        • Li D.
        • Fang J.
        • Liu Q.
        • Cao W.
        • Sun X.
        • et al.
        SARS-CoV-2 receptor ACE2 is expressed in human conjunctival tissue, especially in diseased conjunctival tissue.
        Ocul Surf. 2021; 19: 249-251
        • Hogarty D.T.
        • Mackey D.A.
        • Hewitt A.W.
        Current state and future prospects of artificial intelligence in ophthalmology: a review.
        Clin Exp Ophthalmol. 2019; 47: 128-139
        • Fan Y.
        • Yu Z.
        • Peng Z.
        • Xu Q.
        • Tang T.
        • Wang K.
        • et al.
        Machine learning based strategy surpasses the traditional method for selecting the first trial Lens parameters for corneal refractive therapy in Chinese adolescents with myopia.
        Contact Lens Anterior Eye. 2021; 44: 101330
        • 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
        • Musolf A.M.
        • Simpson C.L.
        • Moiz B.A.
        • Long K.A.
        • Portas L.
        • Murgia F.
        • et al.
        Caucasian families exhibit significant linkage of myopia to chromosome 11p.
        Invest Ophthalmol Vis Sci. 2017; 58: 3547-3554
        • Mountford J.
        • Ruston D.
        • Dave T.
        Design variables and fitting philosophies of reverse geometry lenses.
        in: Orthokeratology: principles and Practice. 1st ed. Elsevier, Butterworth-Heinemann2004: 89-91
        • Dietterich T.G.
        An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization.
        Machine Learn. 2000; 40: 139-157
        • Quinonero-Candela J.Q.
        • Rasmussen C.E.
        A unifying view of sparse approximate Gaussian process regression.
        J Machine Learn Res. 2005; 6: 1939-1959
        • Harvey D.
        • Leybourne S.
        • Newbold P.
        Testing the equality of prediction mean squared errors.
        Int J Forecast. 1997; 13: 281-291
        • Wen G.
        • Hornoch K.T.
        • Cowdin R.M.
        • Cotter S.A.
        • Borchert M.
        • Lin J.
        • et al.
        Prevalence of myopia, hyperopia, and astigmatism in non-Hispanic white and Asian children: multi-ethnic pediatric eye disease study.
        Ophthalmology. 2013; : 2109-2116
        • Pan C.W.
        • Tien-Yin W.
        • Raghavan L.
        • Wu R.Y.
        • Zheng Y.F.
        • Lin X.Y.
        • et al.
        Prevalence and risk factors for refractive errors in Indians: the Singapore Indian Eye Study (SINDI).
        Invest Ophthalmol Vis. 2011; 52: 3166-3173
        • Guggenheim J.A.
        • Northstone K.
        • McMahon G.
        • Ness A.R.
        • Deere K.
        • Mattocks C.
        • et al.
        Time outdoors and physical activity as predictors of incident myopia in childhood: a prospective cohort study.
        Invest Ophthalmol Vis Sci. 2012; 53: 2856-2865
        • Chen C.
        • Cheung S.W.
        • Cho P.
        Myopia control using toric orthokeratology (TO-SEE study).
        Invest Ophthalmol Vis Sci. 2013; 54: 6510-6517
        • Jacinto S.R.
        • César V.C.
        • Bernard G.
        • Ramón G.O.
        Myopia control with orthokeratology contact lenses in Spain: refractive and biometric changes.
        Invest Ophthalmol Vis Sci. 2012; 53: 5060
        • Sankaridurg P.
        • Conrad F.
        • Tran H.
        • Zhu J.
        Controlling progression of myopia: optical and pharmaceutical strategies.
        Asia Pac J Ophthalmol (Phila). 2018; 7: 405-414
        • 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: 600-608
        • Waleed A.M.
        • Lua’i A.-I.
        • Wisam S.
        • Sana J.
        Antimicrobial susceptibility of bacterial isolates from the conjunctiva, storage cases and mobile phones of university students using contact lenses.
        Contact Lens Anterior Eye. 2021; 44: 62-66
        • Hogan R.N.
        Potential for transmission of prion disease by contact lenses: an assessment of risk.
        Eye Contact Lens. 2003; 29: S44-S48