Tamaoki Akeno, Kojima Takashi, Tanaka Yoshiki, Hasegawa Asato, Kaga Tatsushi, Ichikawa Kazuo, Tanaka Kiyoshi
Department of Ophthalmology, Japan Community Healthcare Organization Chukyo Hospital, Nagoya, Japan.
Department of Mathematics and System Development, Shinshu University Interdisciplinary Graduate School of Science and Technology, Nagano, Japan.
Transl Vis Sci Technol. 2019 Jun 28;8(3):64. doi: 10.1167/tvst.8.3.64. eCollection 2019 May.
The purpose of this study was to evaluate the prediction accuracy of effective lens position (ELP) after cataract surgery using a multiobjective evolutionary algorithm (MOEA).
Ninety-six eyes of 96 consecutive patients (aged 73.9 ± 8.6 years) who underwent cataract surgery were retrospectively studied; the eyes were randomly distributed to a prediction group (55 eyes) and a verification group (41 eyes). The procedure was repeated randomly 30 times to create 30 data sets for both groups. In the prediction group, based on the parameters of preoperative optical coherence tomography (OCT), biometry, and anterior segment (AS)-OCT, the prediction equation of ELP was created using MOEA and stepwise multiple regression analysis (SMR). Subsequently, the prediction accuracy of ELPs was evaluated and compared with conventional formulas, including SRK/T and the Haigis formula.
The rate of mean absolute prediction error of 0.3 mm or higher was significantly lower in MOEA (mean 4.9% ± 3.2%, maximum 9.8%) than SMR (mean 7.3% ± 4.8%, maximum 24.4%) ( = 0.0323). The median of the correlation coefficient ( = 0.771) between the MOEA predicted and measured ELP was higher than the SRK/T ( = 0.412) and Haigis ( = 0.438) formulas.
The study demonstrated that ELP prediction by MOEA was more accurate and was a method of less fluctuation than that of SMR and conventional formulas.
MOEA is a promising method for solving clinical problems such as prediction of ocular biometry values by simultaneously optimizing several conditions for subjects affected by various complex factors.
本研究旨在评估使用多目标进化算法（MOEA）预测白内障手术后有效晶状体位置（ELP）的准确性。
回顾性研究96例连续接受白内障手术患者（年龄73.9±8.6岁）的96只眼；将这些眼随机分为预测组（55只眼）和验证组（41只眼）。该过程随机重复30次，为两组创建30个数据集。在预测组中，基于术前光学相干断层扫描（OCT）、生物测量和眼前节（AS）-OCT的参数，使用MOEA和逐步多元回归分析（SMR）创建ELP的预测方程。随后，评估ELP的预测准确性，并与包括SRK/T和Haigis公式在内的传统公式进行比较。
MOEA中平均绝对预测误差率为0.3mm或更高的比例（平均4.9%±3.2%，最大9.8%）显著低于SMR（平均7.3%±4.8%，最大24.4%）（P=0.0323）。MOEA预测的ELP与测量的ELP之间的相关系数中位数（r=0.771）高于SRK/T（r=0.412）和Haigis（r=0.438）公式。
该研究表明，MOEA预测ELP更准确，且是一种比SMR和传统公式波动更小的方法。
MOEA是一种有前景的方法，可通过同时优化受各种复杂因素影响的受试者的多个条件来解决诸如眼生物测量值预测等临床问题。
