文献速递白内障与屈光手术

人工晶状体度数计算——大数据方法与现有公式的比较

Intraocular Lens Power Calculation-Comparing Big Data Approaches to Established Formulas.
PubMed 文献 · Am J Ophthalmol · 2025-02-12

该回顾性对照分析纳入886眼(631例患者)单焦点非球面人工晶状体植入术后资料,比较SRK/T、Haigis、Hoffer Q、Holladay I、Castrop V1公式与经典线性模型、回归样条、随机森林回归的预测性能。回归样条模型样本外平均绝对误差(MAE)为0.279、均方根误差(RMSE)为0.359,优于所有传统公式及Castrop公式(MAE=0.284,RMSE=0.359)。线性回归样本外表现与传统公式相似,随机森林因过拟合样本外泛化性差。

要点

  • 回归样条模型样本外MAE=0.279、RMSE=0.359,优于所有传统公式及Castrop公式。
  • Castrop公式在传统公式中误差最低,MAE=0.284、RMSE=0.359。
  • 线性回归样本外预测误差与传统公式相似,随机森林过拟合致样本外泛化性差。

核心结论

  • 允许非线性效应的回归模型(如基于回归样条)为预测白内障术后屈光提供有前景的传统人工晶状体公式替代方案。
  • 线性回归和随机森林模型可降低样本内误差,但其临床效用目前受样本外性能限制。
  • 未来工作应聚焦提高泛化性并将机器学习模型整合到临床实践中,以改善屈光结局,尤其是针对解剖结构不典型的眼。

研究设计与样本

  • 回顾性、比较性人工晶状体度数计算分析。
  • 纳入886眼来自631例患者,均行白内障手术并植入单焦点非球面人工晶状体。
  • 使用IOLMaster 700光学生物测量,术后至少4周评估屈光。
  • 优化5种人工晶状体公式(SRK/T、Haigis、Hoffer Q、Holladay I、Castrop V1)的公式常数,以均方根误差(RMSE)为优化指标。
  • 回归模型(经典线性模型、回归样条、随机森林回归)在按眼轴长度(正常、短、长、随机)分类的4个数据集上训练,以平均绝对误差(MAE)、RMSE和预测误差方差评估样本内与样本外预测性能。

主要发现

  • 回归模型在样本内预测误差上优于传统人工晶状体公式。
  • 总体而言,线性回归模型在样本外预测误差方面与传统公式表现相似。
  • 最低样本外预测误差(MAE=0.279,RMSE=0.359)由通过回归样条将部分协变量(R2、AL、CCT)效应建模为非线性效应的模型实现。
  • 该模型优于所有传统公式及Castrop公式,Castrop公式在传统公式中误差最低(MAE=0.284,RMSE=0.359)。
  • 随机森林回归样本内表现强,但因过拟合导致样本外泛化性差。

关键数值与推荐

  • 主要结局指标为MAE、RMSE和预测误差方差。
  • 回归样条模型样本外MAE=0.279、RMSE=0.359。
  • Castrop公式MAE=0.284、RMSE=0.359。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

PURPOSE: To evaluate the predictive performance of traditional intraocular lens (IOL) power calculation formulas (e.g., SRK/T, Haigis, Hoffer Q, and Holladay I) compared to advanced regression models, including classical linear models, regression splines, and random forest regression, in predicting postoperative refraction following cataract surgery. DESIGN: Retrospective, comparative analysis of IOL power calculations. SUBJECTS: The study included 886 eyes from 631 patients who underwent cataract surgery with monofocal aspherical IOL implantation. METHODS: Biometric measurements were obtained using optical biometry (IOLMaster 700), and postoperative refraction was assessed at least 4 weeks after surgery. Formula constants for 5 IOL formulas (SRK/T, Haigis, Hoffer Q, Holladay I and Castrop V1) were optimized using root mean squared error (RMSE). Regression models (classical linear model, regression splines, and random forest regression) were trained on 4 datasets categorized by axial length (AL); normal, short, long, and random. Model performance was assessed using mean absolute error (MAE), RMSE, and prediction error variance, for both in-sample and out-of-sample predictions. MAIN OUTCOME MEASURES: The primary parameters measured were MAE, RMSE, and prediction error variance. RESULTS: Regression models outperformed traditional IOL formulas in in-sample prediction error. Overall, linear regression models performed similarly to traditional formulas with respect to out-of-sample prediction error. The lowest out-of-sample prediction error (MAE = 0.279, RMSE = 0.359) was achieved with a model where effects of some covariates (R2, AL, CCT) were modelled as nonlinear via regression splines. This model outperformed all traditional formulas, and the Castrop formula, which had the lowest errors among the formulas (MAE = 0.284, RMSE = 0.359). Random forest regression showed strong in-sample performance but poor out-of-sample generalizability due to overfitting. CONCLUSIONS: Regression models which allow for nonlinear effects, e.g. based on regression splines, provide a promising alternative to traditional IOL formulas for predicting postoperative refraction. Linear regression and random forest regression models can reduce in-sample error, however, their clinical utility is currently limited by out-of-sample performance. Future work should focus on improving generalizability and integrating machine learning models into clinical practice to enhance refractive outcomes, especially for eyes with atypical anatomy.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Redden LD, Grubauer B, Hoffmann P, et al. Intraocular Lens Power Calculation-Comparing Big Data Approaches to Established Formulas. Am J Ophthalmol. 2025. PMID: 39952344. doi:10.1016/j.ajo.2025.02.010

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。