Ray tracing intraocular lens calculation performance improved by AI-powered postoperative lens position prediction.
Ray tracing intraocular lens calculation performance improved by AI-powered postoperative lens position prediction.
复制标题
通过人工智能驱动的术后晶状体位置预测提高了光线追踪人工晶状体计算性能。
DOI：
10.1136/bjophthalmol-2021-320283
复制
发表时间：
2023-04
影响因子：
4.1
通讯作者：
Nallasamy, Nambi
中科院分区：
文献类型：
--
作者：
Li, Tingyang;Reddy, Aparna;Stein, Joshua D.;Nallasamy, Nambi
评估采用机器学习（ML）方法准确预测术后前房深度（ACD）是否可改善常用光线追踪屈光度计算套件（OKULIX）的白内障手术屈光预测性能。密歇根大学凯洛格眼科中心收集了4357名白内障患者的4357只眼睛的数据集。使用先前开发的基于机器学习的方法，根据使用Lenstar LS 900光学生物计测量的术前生物统计学来预测术后ACD。使用标准OKULIX术后ACD预测和基于ML的术后ACD预测计算屈光预测。使用折射预测中的平均绝对误差（MAE）和中值绝对误差（MedAE）作为度量，评估了具有和不具有基于ML的ACD预测的射线追踪方法的性能。用ML预测ACD替代标准OKULIX术后ACD，MAE（归零平均误差后1.7%）和MedAE（归零平均误差后2.1%）均出现统计学显著性降低。ML预测的ACD显著改善了短眼轴和长眼轴的性能（p < 0.01）。使用ML供电的术后ACD预测方法可以提高OKULIX射线追踪套件的预测准确性，临床上很小，但具有统计学意义，在长眼中效果最大。
To assess whether incorporating a machine learning (ML) method for accurate prediction of postoperative anterior chamber depth (ACD) improves cataract surgery refraction prediction performance of a commonly used ray tracing power calculation suite (OKULIX). A dataset of 4357 eyes of 4357 cataract patients was gathered at the Kellogg Eye Center, University of Michigan. A previously developed machine learning-based method was used to predict the postoperative ACD based on preoperative biometry measured with the Lenstar LS900 optical biometer. Refraction predictions were computed with standard OKULIX postoperative ACD predictions and ML-based predictions of postoperative ACD. The performance of the ray tracing approach with and without ML-based ACD prediction was evaluated using mean absolute error (MAE) and median absolute error (MedAE) in refraction prediction as metrics. Replacing the standard OKULIX postoperative ACD with the ML-predicted ACD resulted in statistically significant reductions in both MAE (1.7% after zeroing mean error) and MedAE (2.1% after zeroing mean error). ML-predicted ACD substantially improved performance in eyes with short and long axial lengths (p < 0.01). Using an ML-powered postoperative ACD prediction method improves the prediction accuracy of the OKULIX ray tracing suite by a clinically small but statistically significant amount, with the greatest effect seen in long eyes.
登录
查看更多内容
影响因子：
3
作者：
Li T;Yang K;Stein JD;Nallasamy N
通讯作者：
Nallasamy N
影响因子：
2.8
作者：
Norrby, Sverker
通讯作者：
Norrby, Sverker
影响因子：
4.1
作者：
Norrby, Sverker;Bergman, Rolf;Findl, Oliver
通讯作者：
Findl, Oliver
影响因子：
4.2
作者：
HOLLADAY, JT
通讯作者：
HOLLADAY, JT
影响因子：
3
作者：
Tamaoki, Akeno;Kojima, Takashi;Tanaka, Kiyoshi
通讯作者：
Tanaka, Kiyoshi