Effect of vault on predicting postoperative refractive error for posterior chamber phakic intraocular lens based on a machine learning model.

PURPOSE: To investigate how vault and other biometric variations affect postoperative refractive error of implantable collamer lenses(ICL) by integrating artificial intelligence(AI) and modified vergence formula.

SETTING: Eye and ENT Hospital of Fudan University (EENT FDU, Shanghai, China).

DESIGN: Artificial intelligence and big data based prediction model.

METHODS: We included 2845 eyes who underwent uneventful spherical ICL or toric ICL implantation at EENT FDU, and with manifest refraction results one month after surgery. One eye of each patient was randomly included.Random Forest was used to calculate the postoperative sphere, cylinder, and spherical equivalent by inputting variable ocular parameters. The influence of predicted vault and modified Holladay formula on predicting postoperative refractive error was analyzed. Subgroup analysis of ideal vault(0.25-0.75mm) and extreme vault(<0.25 mm, or >0.75 mm) was performed.

RESULTS: In the test set of both ICLs, all the random forest-based models significantly improved accuracy of predicting postoperative sphere compared to the OCOS calculator(P<0.001). For ideal vault, combination of modified Holladay formula in spherical ICL exhibited highest accuracy(R=0.606). For extreme vault, combination of predicted vault in spherical ICL enhanced R values (R=0.864). Combination of predicted vault and modified Holladay formula was most optimal for toric ICL in all ranges of vault (ideal vault: R=0.516, extreme vault,R=0.334).

CONCLUSION: Our random forest-based calculator, considering vault and variable ocular parameters, illustrated superiority over the existing calculator on our datasets. Choosing an appropriate lens size to control the vault within the ideal range is helpful to avoid refractive surprises.