Evaluation of the Nallasamy Formula: A Stacking Ensemble Machine Learning Method for Refraction Prediction in Cataract Surgery
Preprint
Abstract
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. SYNOPSIS Nallasamy formula, a novel machine learning-based IOL power calculation formula developed based on a dataset of 6893 eyes, achieved significantly better prediction accuracy than five traditional IOL power formulas including Barrett Universal II.Keywords
All Related Versions
- Published version: British Journal of Ophthalmology, 107 (8), 1066.
This publication has 25 references indexed in Scilit:
- The Effect of Testing Distance on Intraocular Lens Power CalculationJournal of Refractive Surgery, 2014
- Indications and Outcomes of Intraocular Lens Exchange During a Recent 5-Year PeriodAmerican Journal of Ophthalmology, 2014
- Reply : Errata in printed Hoffer Q formulaJournal of Cataract & Refractive Surgery, 2007
- Ensemble Methods in Machine Learning2000
- Comparison of immersion ultrasound biometry and partial coherence interferometry for intraocular lens calculation according to HaigisGraefe's Archive for Clinical and Experimental Ophthalmology, 2000
- CorrectionJournal of Cataract & Refractive Surgery, 1994
- The Hoffer Q formula: A comparison of theoretic and regression formulasJournal of Cataract & Refractive Surgery, 1993
- Stacked generalizationNeural Networks, 1992
- Development of the SRK/T intraocular lens implant power calculation formulaJournal of Cataract & Refractive Surgery, 1990
- A three-part system for refining intraocular lens power calculationsJournal of Cataract & Refractive Surgery, 1988