Accuracy of a new intraocular lens power calculation method based on artificial intelligence

González, David Carmona; Bautista, Carlos Palomino

doi:10.1038/s41433-020-0883-3

Cited by 45 publications

(46 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For Japanese patients on Southern Kyushu Island, the performance of BUII was no better than that of the constantly optimized SRK/T and Haigis, supporting the importance of adaptation for the patient group. The accuracy improved with the use of SVR for refining the SRK/T with the training set, as presented in previous studies [ 17 – 20 ]. For Chinese myopic eyes, the machine learning-based calculation showed superior results to the BUII [ 20 ].…”

Section: Discussionsupporting

confidence: 71%

“…Support vector regression (SVR) is a machine learning technique that provides a nonlinear regression function that have at most a certain margin from actually obtained targets (corresponding to prediction errors) for all training data and was as flat as possible (corresponding to minimum amounts of regression coefficients) [ 16 ]. Carmona González et al combined SVR and multivariate adaptive regression spline with training set data using 208 eyes [ 17 ], providing the most accurate performance compared with the 4 conventional formulas. Ladas et al revealed that SVR supervised nonlinear regression machine learning was suitable for optimization of existing IOL power calculation formulas, compared with extreme gradient boosting (XGBoost) and artificial neural network (ANN) [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning adaptation of intraocular lens power calculation for a patient group

Mori

Yamauchi²,

Tokuda

et al. 2021

Eye and Vis

View full text Add to dashboard Cite

Background To examine the effectiveness of the use of machine learning for adapting an intraocular lens (IOL) power calculation for a patient group. Methods In this retrospective study, the clinical records of 1,611 eyes of 1,169 Japanese patients who received a single model of monofocal IOL (SN60WF, Alcon) at Miyata Eye Hospital were reviewed and analyzed. Using biometric metrics and postoperative refractions of 1211 eyes of 769 patients, constants of the SRK/T and Haigis formulas were optimized. The SRK/T formula was adapted using a support vector regressor. Prediction errors in the use of adapted formulas as well as the SRK/T, Haigis, Hill-RBF and Barrett Universal II formulas were evaluated with data from 395 eyes of 395 distinct patients. Mean prediction errors, median absolute errors, and percentages of eyes within ± 0.25 D, ± 0.50 D, and ± 1.00 D, and over + 0.50 D of errors were compared among formulas. Results The mean prediction errors in the use of the SRT/K and adapted formulas were smaller than the use of other formulas (P < 0.001). In the absolute errors, the Hill-RBF and adapted methods were better than others. The performance of the Barrett Universal II was not better than the others for the patient group. There were the least eyes with hyperopic refractive errors (16.5%) in the use of the adapted formula. Conclusions Adapting IOL power calculations using machine learning technology with data from a particular patient group was effective and promising.

show abstract

Section: Discussionsupporting

confidence: 71%

Section: Introductionmentioning

confidence: 99%

Machine learning adaptation of intraocular lens power calculation for a patient group

Mori

Yamauchi²,

Tokuda

et al. 2021

Eye and Vis

View full text Add to dashboard Cite

show abstract

“…Daneben wurden mit dem hochauflösenden optischen Kohärenztomografen für den vorderen Augenabschnitt Casia 2 (Tomey, Nürnberg) die interne Vorderkammertiefe ( Generell gilt, dass mit der Anzahl der potenziellen Effektgrößen die Anzahl der benötigten Trainingsdatensätze ansteigt. Können Teile der Vorhersage durch ein belastbares physikalisches Modell beschrieben werden [3], so können diese Teile der Vorhersage in das Berechnungsschema eingebaut werden, sodass die Komplexität des Algorithmus reduziert werden kann und sich damit die Anzahl der benötigten Trainingsdatensätze reduziert. Genau dieses Vorgehen wird im vorliegenden Artikel beschrieben: Hier soll der physikalische Anteil der Berechnung von Intraokularlinsen, der bspw.…”

Section: Patienten Und Methodenunclassified

Artificial Intelligence, Machine Learning and Calculation of Intraocular Lens Power

Langenbucher

Szentmáry

Wendelstein

et al. 2020

Klin Monbl Augenheilkd

View full text Add to dashboard Cite

Background and Purpose In the last decade, artificial intelligence and machine learning algorithms have been more and more established for the screening and detection of diseases and pathologies, as well as for describing interactions between measures where classical methods are too complex or fail. The purpose of this paper is to model the measured postoperative position of an intraocular lens implant after cataract surgery, based on preoperatively assessed biometric effect sizes using techniques of machine learning. Patients and Methods In this study, we enrolled 249 eyes of patients who underwent elective cataract surgery at Augenklinik Castrop-Rauxel. Eyes were measured preoperatively with the IOLMaster 700 (Carl Zeiss Meditec), as well as preoperatively and postoperatively with the Casia 2 OCT (Tomey). Based on preoperative effect sizes axial length, corneal thickness, internal anterior chamber depth, thickness of the crystalline lens, mean corneal radius and corneal diameter a selection of 17 machine learning algorithms were tested for prediction performance for calculation of internal anterior chamber depth (AQD_post) and axial position of equatorial plane of the lens in the pseudophakic eye (LEQ_post). Results The 17 machine learning algorithms (out of 4 families) varied in root mean squared/mean absolute prediction error between 0.187/0.139 mm and 0.255/0.204 mm (AQD_post) and 0.183/0.135 mm and 0.253/0.206 mm (LEQ_post), using 5-fold cross validation techniques. The Gaussian Process Regression Model using an exponential kernel showed the best performance in terms of root mean squared error for prediction of AQDpost and LEQpost. If the entire dataset is used (without splitting for training and validation data), comparison of a simple multivariate linear regression model vs. the algorithm with the best performance showed a root mean squared prediction error for AQD_post/LEQ_post with 0.188/0.187 mm vs. the best performance Gaussian Process Regression Model with 0.166/0.159 mm. Conclusion In this paper we wanted to show the principles of supervised machine learning applied to prediction of the measured physical postoperative axial position of the intraocular lenses. Based on our limited data pool and the algorithms used in our setting, the benefit of machine learning algorithms seems to be limited compared to a standard multivariate regression model.

show abstract

“…However, key limitations exist among recently-published ML-based IOL calculation methods: (1) performance comparisons limited to older generation formulas, [6] (2) failure to achieve statistically significant improvement over current generation formulas, [7] and (3) small datasets that leave the robustness and generalizability of methods in question. [8] With a goal of advancing the understanding of IOL power selection for general cataract patients and improving refraction prediction accuracy, in the presented study, we developed a novel machine learningbased IOL power calculation method, the Nallasamy formula, based on a large dataset of 5016 cataract patients. In this model, we employed ensemble machine learning methods and novel data augmentation methods.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of the Nallasamy Formula: A Stacking Ensemble Machine Learning Method for Refraction Prediction in Cataract Surgery

Stein

Nallasamy

2021

Preprint

View full text Add to dashboard Cite

Aims: To develop a new intraocular lens (IOL) power selection method with improved accuracy for general cataract patients receiving Alcon SN60WF lenses. Methods and Analysis: A total of 5016 patients (6893 eyes) who underwent cataract surgery at University of Michigan's Kellogg Eye Center and received the Alcon SN60WF lens were included in the study. A machine learning-based method was developed using a training dataset of 4013 patients (5890 eyes), and evaluated on a testing dataset of 1003 patients (1003 eyes). Each eye had a complete profile of preoperative biometry, the implanted IOL power, and postoperative refraction. The performance of our method was compared to that of Barrett Universal II, Haigis, Hoffer Q, Holladay 1, and SRK/T. Results: MAE of the Nallasamy formula in the testing dataset was 0.312 Diopters (MedAE = 0.242 D). Performance of existing methods were as follows: Barrett Universal II MAE = 0.328 D (MedAE = 0.256 D), Haigis MAE = 0.363 D (MedAE = 0.289 D), Hoffer Q MAE = 0.404 D (MedAE = 0.331 D), Holladay 1 MAE = 0.371 D (MedAE = 0.298 D) and SRK/T MAE = 0.376 D (MedAE = 0.300 D). The Nallasamy formula performed significantly better than all five existing methods based on the paired Wilcoxon test with Bonferroni correction (p-value < 0.05). Conclusions: Nallasamy formula outperformed the five methods studied (including Barrett Universal II) on overall MAE and MedAE, percentage of eyes within 0.5 D of prediction, as well as MAE in short, medium, and long axial length eyes.

show abstract

Accuracy of a new intraocular lens power calculation method based on artificial intelligence

Cited by 45 publications

References 12 publications

Machine learning adaptation of intraocular lens power calculation for a patient group

Machine learning adaptation of intraocular lens power calculation for a patient group

Artificial Intelligence, Machine Learning and Calculation of Intraocular Lens Power

Evaluation of the Nallasamy Formula: A Stacking Ensemble Machine Learning Method for Refraction Prediction in Cataract Surgery

Contact Info

Product

Resources

About