Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Michigan, USA.
Kellogg Eye Center, Department of Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, Michigan, USA.
Br J Ophthalmol. 2022 Sep;106(9):1222-1226. doi: 10.1136/bjophthalmol-2020-318321. Epub 2021 Apr 9.
To assess whether incorporating a machine learning (ML) method for accurate prediction of postoperative anterior chamber depth (ACD) improves the refraction prediction performance of existing intraocular lens (IOL) calculation formulas.
A dataset of 4806 patients with cataract was gathered at the Kellogg Eye Center, University of Michigan, and split into a training set (80% of patients, 5761 eyes) and a testing set (20% of patients, 961 eyes). A previously developed ML-based method was used to predict the postoperative ACD based on preoperative biometry. This ML-based postoperative ACD was integrated into new effective lens position (ELP) predictions using regression models to rescale the ML output for each of four existing formulas (Haigis, Hoffer Q, Holladay and SRK/T). The performance of the formulas with ML-modified ELP was compared using a testing dataset. Performance was measured by the mean absolute error (MAE) in refraction prediction.
When the ELP was replaced with a linear combination of the original ELP and the ML-predicted ELP, the MAEs±SD (in Diopters) in the testing set were: 0.356±0.329 for Haigis, 0.352±0.319 for Hoffer Q, 0.371±0.336 for Holladay, and 0.361±0.331 for SRK/T which were significantly lower (p<0.05) than those of the original formulas: 0.373±0.328 for Haigis, 0.408±0.337 for Hoffer Q, 0.384±0.341 for Holladay and 0.394±0.351 for SRK/T.
Using a more accurately predicted postoperative ACD significantly improves the prediction accuracy of four existing IOL power formulas.
评估机器学习（ML）方法在准确预测术后前房深度（ACD）方面的应用是否可以提高现有的人工晶状体（IOL）计算公式的屈光预测性能。
从密歇根大学凯洛格眼科中心收集了 4806 例白内障患者的数据，并将其分为训练集（80%的患者，5761 只眼）和测试集（20%的患者，961 只眼）。使用先前开发的基于 ML 的方法根据术前生物测量学预测术后 ACD。该基于 ML 的术后 ACD 与新的有效晶状体位置（ELP）预测相结合，使用回归模型对四个现有公式（Haigis、Hoffer Q、Holladay 和 SRK/T）的 ML 输出进行重新缩放。使用测试数据集比较公式的性能。使用均方根误差（MAE）来衡量屈光预测的准确性。
当 ELP 被原始 ELP 和 ML 预测的 ELP 的线性组合取代时，测试集中的 MAE±SD（屈光度）分别为：Haigis 为 0.356±0.329，Hoffer Q 为 0.352±0.319，Holladay 为 0.371±0.336，SRK/T 为 0.361±0.331，明显低于原始公式（Haigis 为 0.373±0.328，Hoffer Q 为 0.408±0.337，Holladay 为 0.384±0.341，SRK/T 为 0.394±0.351）（p<0.05）。
使用更准确预测的术后 ACD 可以显著提高四个现有的 IOL 功率公式的预测准确性。
