Development and Validation of Data-Level Innovation Data-Balancing Machine Learning Models for Predicting Optimal Implantable Collamer Lens Size and Postoperative Vault.
Data-level innovation data-balancing
ICL size
Machine learning
Postoperative vault
Prediction
Journal
Ophthalmology and therapy
ISSN: 2193-8245
Titre abrégé: Ophthalmol Ther
Pays: England
ID NLM: 101634502
Informations de publication
Date de publication:
09 Nov 2023
09 Nov 2023
Historique:
received:
13
09
2023
accepted:
20
10
2023
medline:
9
11
2023
pubmed:
9
11
2023
entrez:
9
11
2023
Statut:
aheadofprint
Résumé
There are only four sizes of implantable collamer lens (ICL) available for selection, which cannot completely fit all patients as a result of the discontinuity of ICL sizes. Sizing an optimal ICL and predicting postoperative vault are still unresolved problems. This study aimed to develop and validate innovative data-level data-balancing machine learning-based models for predicting ICL size and postoperative vault. The patients were randomly assigned to training and internal validation sets in a 4:1 ratio. Feature selection was performed using analysis of variance (ANOVA) and Kruskal-Wallis feature importance methods. Traditional linear regression model and machine learning-based models were used. The accuracy of models was assessed using the area under the curve (AUC) and confusion matrix. A total of 564 patients (1127 eyes) were eligible for this study, consisting of 808 eyes in the training set, 202 eyes in the internal validation set, and 117 eyes in the external validation set. Compared with the traditional linear regression method, the machine learning model bagging tree showed the best performance for ICL size selection, with an accuracy of 84.5% (95% confidence interval (CI) 83.2-85.8%), and the AUC ranged from 0.88 to 0.99; the prediction accuracy of 12.1 mm and 13.7 mm ICL sizes was improved by 49% and 59%, respectively. The bagging tree model achieved the best accuracy [90.2%, (95% CI 88.9-91.5%)] for predicting the postoperative vault, and the AUC ranged from 0.90 to 0.94. The prediction accuracies of internal and external validation dataset for ICL sizing were 82.2% (95% CI 81.1-83.3%) and 82.1% (95% CI 81.1-83.1%), respectively. The innovative data-level data balancing-based machine learning model can be used to predict ICL size and postoperative vault more accurately, which can assist surgeons in choosing optimal ICL size, thus reducing risks of postoperative complications and secondary surgery.
Identifiants
pubmed: 37943481
doi: 10.1007/s40123-023-00841-7
pii: 10.1007/s40123-023-00841-7
doi:
Types de publication
Journal Article
Langues
eng
Subventions
Organisme : Capital's Funds for Health Improvement and Research
ID : 2022-1G-4083
Organisme : National Natural Science Foundation of China
ID : 82171092
Organisme : the National Key R&D Program of China
ID : 2021YFC2702100
Organisme : the National Key R&D Program of China
ID : 2020YFC2008200
Informations de copyright
© 2023. The Author(s).
Références
Chen X, Wang X, Xu Y, et al. Five-year outcomes of EVO implantable collamer lens implantation for the correction of high myopia and super high myopia. Eye Vis. 2021;8:1–8.
doi: 10.1186/s40662-021-00264-0
Nakamura T, Isogai N, Kojima T, et al. Posterior chamber phakic intraocular lens implantation for the correction of myopia and myopic astigmatism: a retrospective 10-year follow-up study. Am J Ophthalmol. 2019;206:1–10.
pubmed: 31078536
doi: 10.1016/j.ajo.2019.04.024
Igarashi A, Shimizu K, Kamiya K. Eight-year follow-up of posterior chamber phakic intraocular lens implantation for moderate to high myopia. Am J Ophthalmol. 2014;157:532–9.
pubmed: 24239774
doi: 10.1016/j.ajo.2013.11.006
Assaf JF, Reinstein DZ, Zakka C, et al. Deep learning-based estimation of implantable collamer lens vault using optical coherence tomography. Am J Ophthalmol. 2023;253:29–36.
pubmed: 37142173
doi: 10.1016/j.ajo.2023.04.008
Cao X, Wu W, Wang Y, et al. Comparison over time of vault in Chinese eyes receiving implantable contact lenses with or without a central hole. Am J Ophthalmol. 2016;172:111–7.
pubmed: 27659350
doi: 10.1016/j.ajo.2016.09.016
Kato S, Shimizu K, Igarashi A. Assessment of low-vault cases with an implantable collamer lens. PLoS ONE. 2020;15: e0241814.
pubmed: 33147267
pmcid: 7641440
doi: 10.1371/journal.pone.0241814
Russo A, Filini O, Savini G, et al. Predictability of the vault after implantable collamer lens implantation using OCT and artificial intelligence in White patient eyes. J Cataract Refract Surg. 2023;49:724.
pubmed: 36913536
pmcid: 10284125
doi: 10.1097/j.jcrs.0000000000001182
Strungaru MH, Rodríguez JG, Weisbrod DJ, et al. Acute angle closure following implantable collamer lens for myopia. J Glaucoma. 2020;29:e74–6.
pubmed: 32366780
doi: 10.1097/IJG.0000000000001533
Alfonso JF, Lisa C, Palacios A, et al. Objective vs subjective vault measurement after myopic implantable collamer lens implantation. Am J Ophthalmol. 2009;147:978–83.
pubmed: 19285654
doi: 10.1016/j.ajo.2009.01.006
Alfonso JF, Lisa C, Abdelhamid A, et al. Three-year follow-up of subjective vault following myopic implantable collamer lens implantation. Graefes Arch Clin Exp Ophthalmol. 2010;248:1827–35.
pubmed: 20333528
doi: 10.1007/s00417-010-1322-0
Kamiya K, Igarashi A, Hayashi K, et al. A multicenter prospective cohort study on refractive surgery in 15011 eyes. Am J Ophthalmol. 2017;175:159–68.
pubmed: 28034710
doi: 10.1016/j.ajo.2016.12.009
Hayakawa H, Kamiya K, Ando W, Takahashi M, Shoji N. Etiology and outcomes of current posterior chamber phakic intraocular lens extraction. Sci Rep. 2020;10:21686.
pubmed: 33303807
pmcid: 7730447
doi: 10.1038/s41598-020-78661-z
Shen Y, Wang L, Jian W, et al. Big-data and artificial-intelligence-assisted vault prediction and EVO-ICL size selection for myopia correction. Br J Ophthalmol. 2023;107:201–6.
pubmed: 34489338
doi: 10.1136/bjophthalmol-2021-319618
Kojima T, Yokoyama S, Ito M, et al. Optimization of an implantable collamer lens sizing method using high-frequency ultrasound biomicroscopy. Am J Ophthalmol. 2012;153:632–7.
pubmed: 22245462
doi: 10.1016/j.ajo.2011.06.031
Nakamura T, Isogai N, Kojima T, Yoshida Y, Sugiyama Y. Implantable collamer lens sizing method based on swept-source anterior segment optical coherence tomography. Am J Ophthalmol. 2018;187:99–107.
pubmed: 29294311
doi: 10.1016/j.ajo.2017.12.015
Kang EM, Ryu IH, Lee G, et al. Development of a web-based ensemble machine learning application to select the optimal size of posterior chamber phakic intraocular lens. Transl Vis Sci Technol. 2021;10:5–5.
pubmed: 34111253
pmcid: 8107636
doi: 10.1167/tvst.10.6.5
Moscato V, Picariello A, Sperlí G. A benchmark of machine learning approaches for credit score prediction. Expert Syst Appl. 2021;165: 113986.
doi: 10.1016/j.eswa.2020.113986
Gupta P, Varshney A, Khan MR, et al. Unbalanced credit card fraud detection data: a machine learning-oriented comparative study of balancing techniques. Procedia Comput Sci. 2023;218:2575–84.
doi: 10.1016/j.procs.2023.01.231
Madani M, Motameni H, Mohamadi H. KNNGAN: an oversampling technique for textual imbalanced datasets. J Supercomput. 2023;79:5291–326.
doi: 10.1007/s11227-022-04851-3
Wang Y, Zhang H, Wei Y, et al. An evolutionary computation-based machine learning for network attack detection in big data traffic. Appl Soft Comput. 2023;138:110184.
doi: 10.1016/j.asoc.2023.110184
Zhang H, Yang W, Yi W, et al. Imbalanced data based fault diagnosis of the chiller via integrating a new resampling technique with an improved ensemble extreme learning machine. J Build Eng. 2023;70:106338.
doi: 10.1016/j.jobe.2023.106338
Zhao S, Meng J, Wekesa JS, Luan Y. Identification of small open reading frames in plant lncRNA using class-imbalance learning. Comput Biol Med. 2023;157:106773.
pubmed: 36924731
doi: 10.1016/j.compbiomed.2023.106773
Herawan T, Deris MM, Abawajy J. Proceedings of the first international conference on advanced data and information engineering (DaEng-2013). Springer; 2013.
Muslim MA, Nikmah TL, Pertiwi DAA, Dasril Y. New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning. Intell Syst Appl. 2023;18: 200204.
Khan SH, Hayat M, Bennamoun M, Sohel FA, Togneri R. Cost-sensitive learning of deep feature representations from imbalanced data. IEEE Trans Neural Netw Learn Syst. 2017;29:3573–87.
pubmed: 28829320
Mathew J, Pang CK, Luo M, Leong WH. Classification of imbalanced data by oversampling in kernel space of support vector machines. IEEE Trans Neural Netw Learn Syst. 2017;29:4065–76.
pubmed: 29028213
doi: 10.1109/TNNLS.2017.2751612
Koziarski M. Potential anchoring for imbalanced data classification. Pattern Recogn. 2021;120: 108114.
doi: 10.1016/j.patcog.2021.108114
Lim P, Goh CK, Tan KC. Evolutionary cluster-based synthetic oversampling ensemble (eco-ensemble) for imbalance learning. IEEE Trans Cybern. 2016;47:2850–61.
pubmed: 27337735
doi: 10.1109/TCYB.2016.2579658
Ng WW, Hu J, Yeung DS, Yin S, Roli F. Diversified sensitivity-based undersampling for imbalance classification problems. IEEE Trans Cybern. 2014;45:2402–12.
pubmed: 25474818
doi: 10.1109/TCYB.2014.2372060
Park J, Kwon S, Jeong S-P. A study on improving turnover intention forecasting by solving imbalanced data problems: focusing on SMOTE and generative adversarial networks. J Big Data. 2023;10:1–16.
pubmed: 36618886
pmcid: 9808691
doi: 10.1186/s40537-022-00674-4
Ramentol E, Gondres I, Lajes S, et al. Fuzzy-rough imbalanced learning for the diagnosis of high voltage circuit breaker maintenance: the SMOTE-FRST-2T algorithm. Eng Appl Artif Intell. 2016;48:134–9.
doi: 10.1016/j.engappai.2015.10.009
Lin SY, Law KM, Yeh YC, et al. Applying machine learning to carotid sonographic features for recurrent stroke in patients with acute stroke. Front Cardiovasc Med. 2022;9:804410.
pubmed: 35155629
pmcid: 8833232
doi: 10.3389/fcvm.2022.804410
Rikta ST, Uddin KMM, Biswas N, et al. XML-GBM lung: an explainable machine learning-based application for the diagnosis of lung cancer. J Pathol Inform. 2023;14:100307.
pubmed: 37025326
pmcid: 10070138
doi: 10.1016/j.jpi.2023.100307
Bogdanovic B, Eftimov T, Simjanoska M. In-depth insights into Alzheimer’s disease by using explainable machine learning approach. Sci Rep. 2022;12:6508.
pubmed: 35444165
pmcid: 9021280
doi: 10.1038/s41598-022-10202-2
Branco P, Torgo L, Ribeiro RP. A survey of predictive modeling on imbalanced domains. ACM Comput Surv (CSUR). 2016;49:1–50.
doi: 10.1145/2907070
García V, Mollineda RA, Sánchez JS. Index of balanced accuracy: a performance measure for skewed class distributions. Pattern Recognition and Image Analysis: 4th Iberian Conference, IbPRIA 2009 Póvoa de Varzim, Portugal, June 10–12, 2009 Proceedings 4: 2009.
Ma Y, He H. Imbalanced learning: foundations, algorithms, and applications. 2013. https://doi.org/10.1002/9781118646106.fmatter .
Sammut C, Webb GI. Encyclopedia of machine learning. Springer; 2011.
Igarashi A, Shimizu K, Kato S, Kamiya K. Predictability of the vault after posterior chamber phakic intraocular lens implantation using anterior segment optical coherence tomography. J Cataract Refract Surg. 2019;45:1099–104.
pubmed: 31174990
doi: 10.1016/j.jcrs.2019.02.020
Wang F, Wang D, Song M, et al. MiRNA-155-5p reduces corneal epithelial permeability by remodeling epithelial tight junctions during corneal wound healing. Curr Eye Res. 2020;45:904–13.
pubmed: 31852252
doi: 10.1080/02713683.2019.1707229
Sha F, Saul L, Lee D. Multiplicative updates for nonnegative quadratic programming in support vector machines. Adv Neural Inf Process Syst. 2002;15.
Maes F, Vandermeulen D, Suetens P. Medical image registration using mutual information. Proc IEEE. 2003;91:1699–722.
doi: 10.1109/JPROC.2003.817864
Wu G, Chang EY. Class-boundary alignment for imbalanced dataset learning. In: ICML 2003 workshop on learning from imbalanced data sets II, Washington, DC 2003.
Patcha A, Park J-M. An overview of anomaly detection techniques: existing solutions and latest technological trends. Comput Netw. 2007;51:3448–70.
doi: 10.1016/j.comnet.2007.02.001
Kamiya K, Ryu IH, Yoo TK, et al. Prediction of phakic intraocular lens vault using machine learning of anterior segment optical coherence tomography metrics. Am J Ophthalmol. 2021;226:90–9.
pubmed: 33577789
doi: 10.1016/j.ajo.2021.02.006