Postoperative vault prediction for phakic implantable collamer lens surgery: LASSO formulas

VAULT: vault accuracy using deep learning technology: new image-based artificial intelligence model for predicting implantable collamer lens postoperative vault

PURPOSE

To develop an accurate deep learning model to predict postoperative vault of phakic implantable collamer lenses (ICLs).

SETTING

Parkhurst NuVision LASIK Eye Surgery, San Antonio, Texas.

DESIGN

Retrospective machine learning study.

METHODS

437 eyes of 221 consecutive patients who underwent ICL implantation were included. A neural network was trained on preoperative very high-frequency digital ultrasound images, patient demographics, and postoperative vault.

RESULTS

3059 images from 437 eyes of 221 patients were used to train the algorithm on individual ICL sizes. The 13.7 mm size was excluded because of insufficient data. A mean absolute error of 66.3 μm, 103 μm, and 91.8 μm were achieved with 100%, 99.0%, and 96.6% of predictions within 500 μm for the 12.1 mm, 12.6 mm, and 13.2 mm sizes, respectively.

CONCLUSIONS

This deep learning model achieved a high level of accuracy of predicting postoperative ICL vault with the overwhelming majority of predictions successfully within a clinically acceptable margin of vault.

Monte-Carlo simulation for calculating phakic supplementary lenses based on a thick and thin lens model using anterior segment OCT data

BACKGROUND

Phakic lenses (PIOLs, the most common and only disclosed type being the implantable collamer lens, ICL) are used in patients with large or excessive ametropia in cases where laser refractive surgery is contraindicated. The purpose of this study was to present a strategy based on anterior segment OCT data for calculating the refraction correction (REF) and the change in lateral magnification (ΔM) with ICL implantation.

METHODS

Based on a dataset (N = 3659) containing Casia 2 measurements, we developed a vergence-based calculation scheme to derive the REF and gain or loss in ΔM on implantation of a PIOL having power PIOLP. The calculation concept is based on either a thick or thin lens model for the cornea and the PIOL. In a Monte-Carlo simulation considering, all PIOL steps listed in the US patent 5,913,898, nonlinear regression models for REF and ΔM were defined for each PIOL datapoint.

RESULTS

The calculation shows that simplifying the PIOL to a thin lens could cause some inaccuracies in REF (up to ½ dpt) and ΔM for PIOLs with high positive power. The full range of listed ICL powers (- 17 to 17 dpt) could correct REF in a range from - 17 to 12 dpt with a change in ΔM from 17 to - 25%. The linear regression considering anterior segment biometric data and the PIOLP was not capable of properly characterizing REF and ΔM, whereas the nonlinear model with a quadratic term for the PIOLP showed a good performance for both REF and ΔM prediction.

CONCLUSION

Where PIOL design data are available, the calculation concept should consider the PIOL as thick lens model. For daily use, a nonlinear regression model can properly predict REF and ΔM for the entire range of PIOL steps if a vergence calculation is unavailable.

Immediate Sequential Bilateral Implantable Collamer Lens Surgery Is Safe and Effective

PURPOSE

To assess the clinical outcomes and safety profiles of patients who underwent immediate sequential bilateral phakic lens surgery.

METHODS

This retrospective multicenter study included 254 consecutive patients (508 eyes) who underwent bilateral same-day Implantable Collamer Lens (ICL) (STAAR Surgical) surgery. The authors focused on 1-year postoperative clinical outcomes and adverse events.

RESULTS

In the initial cohort, 176 patients (352 eyes) met inclusion criteria. Of these, 335 eyes underwent myopic ICL placement, and 17 eyes received a hyperopic ICL. Notably, 87% of eyes achieved ±0.50 diopters (D) and 95% achieved ±1.00 D of the intended refraction. One year postoperatively, 78% of eyes demonstrated optimal vaulting (250 to 750 µm), with a significant 19% reduction in vaulting observed over the 12 months (P < .001). Only minor adverse events, including early cataract formation (1 case), secondary toric ICL rotation (3 cases), and ICL exchange due to inappropriate vaulting (6 cases), were noted.

CONCLUSIONS

The findings corroborate the safety and efficacy of immediate sequential bilateral phakic lens surgery and indicate its potential as a treatment option. The low incidence of minor adverse events further reinforces its favorable safety profile. [J Refract Surg. 2024;40(5):e313-e320.].

Implantable Collamer Lens Procedure Planning: A Review of Global Approaches

More than 2 million implantable collamer lenses (ICLs) have been implanted worldwide. With a central port to improve aqueous flow through the ICL, the latest iteration of this phakic intraocular lens (pIOL) has been shown to have stable outcomes with very low rates of adverse events. However, correct planning and ICL size selection continue to be important to achieve an optimal vault. Shallow or excessive vaults are not complications in and of themselves but may increase the risk of complications. Historically, surgeons have relied on measurements of anterior chamber depth (ACD) and manual, caliper-measured white-to-white (WTW) distance to select the ICL size. New diagnostic and imaging technologies such as optical coherence tomography (OCT) and ultrasound biomicroscopy (UBM) provide additional opportunities for visualization and measurement of the intraocular dimensions involved in phakic intraocular lens implantation, including sulcus-to-sulcus (STS) and angle-to-angle (ATA) diameters. This paper reviews various approaches to ICL planning and sizing that have been published in the peer-reviewed literature, all of which produce acceptable results for predicting vault and size selection. Surgeons may also want to identify a methodology for patient evaluation and ICL size selection that best aligns with their personal preferences, diagnostic technology, and familiarity with analytical optimization tools.

Utilization of the Reinstein ICL Sizing Formula With Hand-held Ultrasound Biomicroscopy Measurements

PURPOSE

To evaluate the accuracy of the Reinstein formula with hand-held ultrasound biomicroscopy (UBM) measurements for sizing of the Implantable Collamer Lens (ICL).

METHODS

A total of 107 myopic eyes of 57 patients implanted with the ICL were included in the study. The size of the ICL was selected based on the manufacturer's recommendations. Agreement between the vault predicted by the Reinstein formula and the vault measured postoperatively was analyzed with Bland-Altman plots.

RESULTS

A total of 95% and 81% of patients had a postoperative vault ranging from 150 to 1,000 and 250 to 750 μm, respectively. The mean vault predicted by the Reinstein formula and the postoperative vault in the current study were 580 ± 181 and 547 ± 200 μm, respectively. The size recommendations of the Reinstein formula and the formula provided by the manufacturer, the Kojima formula, and the Dougherty formula overlapped in 50%, 57%, and 49% of eyes, respectively.

CONCLUSIONS

The results show that the Reinstein formula combined with a hand-held UBM provides reliable sizing predictions of the ICL. However, considering that robotic UBM measurements have demonstrated a narrower range of deviation in predicting vault depth in previous studies, a direct comparison study between robotic UBM and hand-held UBM measurements is necessary to fully assess the limitations of combining hand-held UBM with the Reinstein formula. [J Refract Surg. 2024;40(3):e142-e147.].

Comparative evaluation of multiple nomograms for predicting postoperative vault after implantable collamer lens surgery

PURPOSE

To compare the vault predictability of most available implantable collamer lens (ICL) sizing nomograms and identify which preoperative measurements are predictive of vault.

SETTING

Private practice in Draper, Utah.

DESIGN

Retrospective chart review.

METHODS

This study was a retrospective analysis of 209 eyes of 106 patients who underwent STAAR Surgical ICL implantation. Analyses were performed based on the availability of preoperative parameters, varying the number of eyes for each test. Mean absolute error (MAE) of predicted vs actual postoperative vault was calculated for each nomogram. The frequency of Kim, Rocamora (least absolute shrinkage and selection operator-optical coherence tomography), Russo, and Reinstein recommending the correct ICL size in instances when Parkhurst, optimized white-to-white (WTW), and STAAR could not recommend a definitive ICL size was determined. Univariate and multivariate linear regression analysis was performed between preoperative measurements and vault.

RESULTS

The Kim, Rocamora, Russo, and Reinstein nomograms had significantly lower MAE of predicted vs actual postoperative vault than the KSV2 and Nakamura V3 nomograms. The Russo formula most frequently recommended the correct ICL size when the Parkhurst, Optimized WTW, and STAAR nomograms could not provide ICL size recommendations. At the 0.05 significance level, anterior chamber depth (ACD), ciliary body inner diameter (CBID), and pupil diameter were the parameters found to have significant correlation with postoperative vault.

CONCLUSIONS

The Kim, Rocamora, Russo, and Reinstein nomograms were the most predictive of vault. Additionally, ACD, CBID, and pupil diameter were found to be significantly correlated with vault and should be considered for use in future ICL sizing nomograms.

Five-year follow-up of a posterior chamber phakic intraocular lens with a central hole for correction of myopia

PURPOSE

To evaluate intermediate and long-term visual outcomes and safety of a phakic intraocular posterior chamber lens with a central hole (ICL V4c) for myopic eyes.

METHODS

Retrospective, consecutive case study of patients that uneventfully received a ICL V4c for myopia correction, with a 5-year postoperative follow-up. Department of Ophthalmology, Goethe University Frankfurt, Germany.

RESULTS

From 241 eyes that underwent ICL implantation, we included 45 eyes with a mean age at surgery of 33 years ± 6 (18-48 years), with a 5 years follow-up. CDVA improved from 0.05logMAR ± 0.15 CDVA preoperatively to  - 0.00 ± 0,07 at 5 years and did not change significantly from 3 to 5 years' time (p = 0.266). The mean spherical equivalent (SE) improved from -10.13D ± 3.39 to  - 0.45D ± 0.69. The change in endothelial cell count showed a mean decrease of 1.9% per year throughout the follow-up. Safety and efficacy index were 1.16 and 0.78, respectively. Cataract formation was seen in 2 of 241 eyes (0.8%), but in none of the 45 eyes that finished the 5-year follow-up.

CONCLUSIONS

Our data show a good intermediate and long-term stability, efficiency, and safety of ICL V4c phakic lenses in myopic eyes comparable to other known literature.

Exploring Nomograms for Implantable Collamer Lens Size Selection in Myopia: A Literature-based Compilation

Purpose

To provide a comprehensive guide of all implantable collamer lens (ICL) sizing nomograms and the respective preoperative diagnostic devices that are required. This guide would help clinicians in choosing the appropriate ICL size for myopic patients to optimize postoperative vault height.

Methods

A literature search of peer-reviewed journals describing methods and postoperative outcomes of ICL sizing was conducted. Research articles containing ICL nomograms or formulas were identified from this search. Preoperative variables necessary for these nomograms and the required diagnostic devices to measure these parameters such as topography, biometry, or ultrasound biomicroscopy (UBM) were noted. An additional search was conducted to identify artificial intelligence (AI) or machine learning (ML)-derived nomograms.

Results

Eighteen ICL sizing nomograms were identified through literature search. Five of these nomograms are available for use and require topography or biometry devices. Of these, four include the manufacturer's, optimized white-to-white (WTW), Kang, Kim, and Rocamora Nomograms. Eight of the 18 nomograms available for use require UBM. Eight of these include the Kojima, Nakamura, KS, ZZ, Dougherty, Parkhurst, Russo, and Reinstein Nomograms. Four of the 18 nomograms are ML-derived including Shen, Rocamora, Russo, and Kang Nomograms.

Conclusion

ICL nomograms are a vital tool in helping clinicians select the right ICL size for myopic patients to optimize postoperative vault reducing risk of postoperative complications. Based on available diagnostic devices such as topography, biometry, or UBM clinicians can integrate specific nomograms into practice.

Diagnostic Techniques to Increase the Safety of Phakic Intraocular Lenses

Preoperative and postoperative diagnostics play an important role in ensuring the safety of patients with phakic intraocular lenses (pIOLs). The risk of endothelial cell loss can be addressed by regularly measuring the endothelial cell density using specular microscopy and considering the endothelial cell loss rate and the endothelial reserve in accordance with the patient's age when deciding whether to explant a pIOL. The anterior chamber morphometrics, including the anterior chamber depth and the distance between the pIOL and the endothelium, measured using Scheimpflug tomography and anterior segment optical coherence tomography (AS-OCT), can help to assess the risk of the endothelial cell loss. In patients undergoing posterior chamber pIOL implantation, accurate prediction of the vault and its postoperative measurements using AS-OCT or Scheimpflug tomography are important when assessing the risk of anterior subcapsular cataract and secondary glaucoma. Novel approaches based on ultrasound biomicroscopy and AS-OCT have been proposed to increase the vault prediction accuracy and to identify eyes in which prediction errors are more likely. Careful patient selection and regular postoperative follow-up visits can reduce the complication risk and enable early intervention if a complication occurs.

Rotational Stability After Implantation of Two Different Phakic Toric Intraocular Lenses

PURPOSE

To compare clinical outcomes and rotational stability of the toric implantable Collamer lens (TICL) and toric implantable phakic contact lens (TIPCL).

METHODS

Charts were reviewed from January 2011 to January 2023 to identify all TICLs and TIPCLs implanted by a single surgeon. Implant size was generally chosen according to the manufacturer's recommendation, but 15 TIPCLs 0.25 mm larger than recommended to increase vaulting were included.

RESULTS

Eighty-four TICLs and 98 TIPCLs were identified and yielded excellent refractive and visual results in eyes with high myopic astigmatism at the last follow-up visit. No case of acute glaucoma or cataract induction was observed. In total, 15 (8.2%) rotated lenses were recorded; 2 (2.4%) TICLs and 13 (13.3%) TIPCLs (P = .013). Eyes in both groups were similar in preoperative spherical equivalent, cylinder, white-to-white distance, anterior chamber depth (ACD), anterior chamber angle, and mean follow-up times (P = .925, .673, .822, .794, .358, and .873, respectively). Average TICL size was larger than TIPCL size (P < .001). Rotation of the lenses was positively correlated with cylinder and negatively correlated with ACD but not with vaulting (P = .001, r = 0.253; P = .011, r = -0.193; P = .488, r = -0.057; respectively). Vaulting was positively correlated with preoperative ACD (P ≤ .001, r = .329). In eyes with a rotated TIPCL, preoperative cylinder was higher and ACD was shallower than in eyes with a stable TIPCL (P = .001 and .007, respectively). Increasing the implant size had no significant effect on rotation rate (P = .685).

CONCLUSIONS

Although both implants were safe and effective in highly myopic eyes, TICL rotated less frequently than TIPCL and required fewer secondary interventions. Rotation was correlated with preoperative cylinder and ACD but not lens vaulting. [J Refract Surg. 2023;39(7):463-472.].

Development of an implantable collamer lens sizing model: a retrospective study using ANTERION swept-source optical coherence tomography and a literature review

BACKGROUND

Optimal sizing for phakic intraocular lens (EVO-ICL with KS-AquaPort) implantation plays an important role in preventing postoperative complications. We aimed to formulate optimal lens sizing using ocular biometric parameters measured with a Heidelberg anterior segment optical coherence tomography (AS-OCT) device.

METHODS

We retrospectively analyzed 892 eyes of 471 healthy subjects treated with an intraocular collamer lens (ICL) and assigned them to either the development (80%) or validation (20%) set. We built vault prediction models using the development set via classic linear regression methods as well as partial least squares and least absolute shrinkage and selection operator (LASSO) regression techniques. We evaluated prediction abilities based on the Bayesian information criterion (BIC) to select the best prediction model. The performance was measured using Pearson's correlation coefficient and the mean squared error (MAE) between the achieved and predicted results.

RESULTS

Measurements of aqueous depth (AQD), anterior chamber volume, anterior chamber angle (ACA) distance, spur-to-spur distance, crystalline lens thickness (LT), and white-to-white distance from ANTERION were highly associated with the ICL vault. The LASSO model using the AQD, ACA distance, and LT showed the best BIC results for postoperative ICL vault prediction. In the validation dataset, the LASSO model showed the strongest correlation (r = 0.582, P < 0.001) and the lowest MAE (104.7 μm).

CONCLUSION

This is the first study to develop a postoperative ICL vault prediction and lens-sizing model based on the ANTERION. As the measurements from ANTERION and other AS-OCT devices are not interchangeable, ANTERION may be used for optimal ICL sizing using our formula. Because our model was developed based on the East Asian population, further studies are needed to explore the role of this prediction model in different populations.