The Zhu-Lu Formula: A Machine Learning-Based Intraocular Lens Power Calculation Formula For Highly Myopic Eyes

To develop a novel machine learning-based intraocular lens (IOL) power calculation formula for highly myopic eyes.

Multicenter retrospective case series.

Totally 1828 highly myopic patients (1828 eyes) undergoing cataract surgery in our hospital were included as internal dataset, and 151 highly myopic patients (151 eyes) from another two hospitals were encompassed as external test dataset. The Zhu-Lu formula was developed based on the eXtreme gradient boosting and the support vector regression algorithms. Its accuracy was compared in the internal and external test datasets with the Barrett Universal II (BUII), Emmetropia Verifying Optical (EVO) 2.0, Kane, Pearl-DGS and RBF 3.0 formulas. 

In the internal test dataset, the Zhu-Lu, RBF 3.0 and BUII ranked top three considering standard deviations (SDs) of prediction errors (PEs). The Zhu-Lu and RBF 3.0 showed significantly lower median absolute errors (MedAEs) than the others. In the external test dataset, the Zhu-Lu, Kane and EVO 2.0 ranked top three considering SDs of PEs. The Zhu-Lu formula showed a comparable MedAE with BUII and EVO 2.0 but significantly lower than Kane, Pearl-DGS and RBF 3.0. The Zhu-Lu formula ranked first regarding the percentages of eyes within ±0.50D of the PE in both test datasets (internal: 80.61%; external: 72.85%). In the axial length subgroup analysis, the prediction error of the Zhu-Lu stayed stably close to zero in all subgroups.

The novel IOL power calculation formula for highly myopic eyes demonstrated improved and stable predictive accuracy compared with other artificial intelligence-based formulas.