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 (ICLs) by integrating artificial intelligence and modified vergence formula.

SETTING

Eye and ENT Hospital of Fudan University, Shanghai, China.

DESIGN

Artificial intelligence and big data-based prediction model.

METHODS

2845 eyes that underwent uneventful spherical ICL or toric ICL implantation and with manifest refraction results 1 month postoperatively were included. 1 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 to 0.75 mm) 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 the accuracy of predicting postoperative sphere compared with the Online Calculation & Ordering System calculator ( P < .001). For ideal vault, the combination of modified Holladay formula in spherical ICL exhibited highest accuracy ( R = 0.606). For extreme vault, the combination of predicted vault in spherical ICL enhanced R values ( R = 0.864). The 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).

CONCLUSIONS

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

Changes of ocular biometry in eyes with posterior chamber phakic intraocular lens implantation

OBJECTIVE

To evaluate changes in biometric variables and intraocular lens (IOL) calculation results after posterior chamber phakic IOL (PCPIOL) implantation.

METHODS

This retrospective, observational study included 65 eyes of 38 patients who underwent PCPIOL (EVO Visian ICL) implantation for correction of myopia. Prior to and a minimum of one year (mean 14.9 months) after EVO Visian ICL implantation, biometric variables and IOL calculation results were compared. Optical biometry, including anterior chamber depth, axial length, flat, steep, and mean keratometry values and IOL calculation results for the Holladay 2, Hoffer Q, Haigis, and SRK/T formulas were measured using the IOLMaster 700 SWEPT Source OCT biometer.

MAIN RESULTS

The mean anterior chamber depth decreased from 3.70±0.22mm to 3.34±0.39mm, the mean axial length increased from 26.61±1.61mm to 26.71±1.66mm, and the mean flat keratometry changed from 42.82±1.86 D to 42.73±1.83 D. These changes were statistically significant. The mean IOL power calculation also revealed a statistically significant decrease with all four formulas (ranging from 0.19 D to 0.30 D) after PCPIOL implantation.

CONCLUSIONS

Biometric variables and IOL calculation results showed statistically significant changes one year after EVO Visian ICL implantations. However, IOL power calculations yielded a decrease of less than 0.50 D, inducing much less refractive deviation in the spectacle plane; and the change was primarily related to an increase in AL measurements. IOL power calculations in eyes with EVO Visian ICL in situ provided satisfactory and reliable results.

Long-term longitudinal changes in axial length in the Caucasian myopic and hyperopic population with a phakic intraocular lens

Purpose

To determine the long‐term longitudinal axial length changes in myopic and hyperopic adults with an iris‐fixated phakic intraocular lens (pIOL).

Methods

The medical records of patients aged ≥18 years with myopia or hyperopia who were treated with pIOL implantation between 1996 and 2011 for refractive correction with a minimum follow‐up of 5 years after pIOL implantation were analyzed. The main outcome measure was change in ocular axial length over time.

Results

149 eyes of 149 myopic patients and 27 hyperopic eyes of 27 patients were included in this study. Mean patient age was 37.1 ± 10.4 years (35% male) in the myopic group and 39.4 ± 9.4 years (4% male) in the hyperopic group. The eyes of the myopic patients showed a significant mean increase in axial length of 0.45 ± 0.61 mm after a mean follow‐up time of 144 ± 38 months (p < 0.001). In 26 eyes (17%), the axial length had increased by ≥1 mm. The mean annual axial length increase was 0.04 ± 0.06 mm. Axial elongation was associated with a higher degree of myopia (p < 0.001) and younger age (p = 0.02). The eyes of the hyperopic patients showed no change in axial length over time.

Conclusions

Myopic eyes corrected with an iris‐fixated pIOL show continuous increase in axial length at an adult age. Although this study is limited to subjects with a pIOL, this is the first time myopization in Caucasian adults has been reported in a large long‐term longitudinal study.