Big-data and artificial-intelligence-assisted vault prediction and EVO-ICL size selection for myopia correction

A comparative study of two phakic posterior chamber implantable lenses

This study aimed to compare the postimplantation clinical outcomes of 2 types of posterior chamber phakic intraocular lenses (IOLs): Visian™ implantable collamer lenses (ICL; EVO+ V5; Staar Surgical, Monrovia, CA) and an implantable phakic contact lens (IPCL) (IPCL V2.0, Care Group Sight Solution, India) to correct high myopia and myopic astigmatism. This retrospective study included patients who had undergone phakic IOL implantation performed by a single surgeon between March 2021 and March 2022. Preoperative assessments included slit-lamp examination, fundus examination, spherical equivalent, uncorrected distant visual acuity (UDVA), corrected distant visual acuity (CDVA), specular microscope parameters, and optical quality analysis system parameters. Postoperative assessments after 1 year included slit-lamp examination to detect adverse effects and spherical equivalent, UDVA, CDVA, specular microscope, optical quality analysis system, and anterior-segment optical coherence tomography. Eighty eyes from 42 patients (47 eyes from 24 patients in the ICL group and 33 eyes from 18 patients in the IPCL group) were included. No statistically significant differences were observed between the 2 groups regarding preoperative parameters. At 1-year postoperatively, the mean UDVA in the ICL and IPCL groups was 0.019 ± 0.040 logMAR and 0.019 ± 0.041 logMAR, respectively. The mean CDVA was 0.001 ± 0.008 logMAR and 0.001 ± 0.007 logMAR in the ICL and IPCL groups, respectively, showing no statistically significant differences. The postoperative parameters did not differ significantly between the 2 groups. The visual acuity and refractive results of both groups were excellent, and both groups exhibited similar efficacy and safety profiles.

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.

The Influence of Lens Position, Vault Prediction, and Posterior Cornea on Phakic Posterior Chamber Intraocular Lens Power

BACKGROUND

Achieving precise refractive outcomes in phakic posterior chamber intraocular lens (pIOL) implantation is crucial for patient satisfaction. This study investigates factors affecting pIOL power calculations, focusing on myopic eyes, and evaluates the potential benefits of advanced predictive models.

DESIGN

Retrospective, single-center, algorithm improvement study.

METHODS

Various variations with different effective lens position (ELP) algorithms were analyzed. The algorithms included a fixed constant model, and a multiple linear regression model and were tested with and without incorporation of the posterior corneal curvature (Rcp). Furthermore, the impact of inserting the postoperative vault, the space between the pIOL and the crystalline lens, into the ELP algorithm was examined, and a simple vault prediction model was assessed.

RESULTS

Integrating Rcp and the measured vault into pIOL calculations did not significantly improve accuracy. Transitioning from constant model approaches to ELP concepts based on linear regression models significantly improved pIOL power calculations. Linear regression models outperformed constant models, enhancing refractive outcomes for both ICL and IPCL pIOL platforms.

CONCLUSIONS

This study underscores the utility of implementing ELP concepts based on linear regression models into pIOL power calculation. Linear regression based ELP models offered substantial advantages for achieving desired refractive outcomes, especially in lower to medium power pIOL models. For pIOL power calculations in both pIOL platforms we tested with preoperative measurements from a Scheimpflug device, we found improved results with the LION 1ICL formula and LION 1IPCL formula. Further research is needed to explore the applicability of these findings to a broader range of pIOL designs and measurement devices.

Developing and validating a clinlabomics-based machine-learning model for early detection of retinal detachment in patients with high myopia

BACKGROUND

Retinal detachment (RD) is a vision-threatening disorder of significant severity. Individuals with high myopia (HM) face a 2 to 6 times higher risk of developing RD compared to non-myopes. The timely identification of high myopia-related retinal detachment (HMRD) is crucial for effective treatment and prevention of additional vision impairment. Consequently, our objective was to streamline and validate a machine-learning model based on clinical laboratory omics (clinlabomics) for the early detection of RD in HM patients.

METHODS

We extracted clinlabomics data from the electronic health records for 24,440 HM and 5607 HMRD between 2015 and 2022. Lasso regression analysis assessed fifty-nine variables, excluding collinear variables (variance inflation factor > 10). Four models based on random forest, gradient boosting machine (GBM), generalized linear model, and Deep Learning Model were trained for HMRD diagnosis and employed for internal validation. An external test of the models was done. Three random data sets were further processed to validate the performance of the diagnostic model. The primary outcomes were the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUCPR) to diagnose HMRD.

RESULTS

Nine variables were selected by all models. Given the AUC and AUCPR values across the different sets, the GBM model was chosen as the final diagnostic model. The GBM model had an AUC of 0.8550 (95%CI = 0.8322-0.8967) and an AUCPR of 0.5584 (95%CI = 0.5250-0.5879) in the training set. The AUC and AUCPR in the internal validation were 0.8405 (95%CI = 0.8060-0.8966) and 0.5355 (95%CI = 0.4988-0.5732). During the external test evaluation, it reached an AUC of 0.7579 (95%CI = 0.7340-0.7840) and an AUCPR of 0.5587 (95%CI = 0.5345-0.5880). A similar discriminative capacity was observed in the three random data sets. The GBM model was well-calibrated across all the sets. The GBM-RD model was implemented into a web application that provides risk prediction for HM individuals.

CONCLUSION

GBM algorithms based on nine features successfully predicted the diagnosis of RD in patients with HM, which will help ophthalmologists to establish a preliminary diagnosis and to improve diagnostic accuracy in the clinic.

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.

Code-Free Machine Learning Approach for EVO-ICL Vault Prediction: A Retrospective Two-Center Study

Purpose

Establishing a development environment for machine learning is difficult for medical researchers because learning to code is a major barrier. This study aimed to improve the accuracy of a postoperative vault value prediction model for implantable collamer lens (ICL) sizing using machine learning without coding experience.

Methods

We used Orange data mining, a recently developed open-source, code-free machine learning tool. This study included eye-pair data from 294 patients from the B&VIIT Eye Center and 26 patients from Kim's Eye Hospital. The model was developed using OCULUS Pentacam data from the B&VIIT Eye Center and was internally evaluated through 10-fold cross-validation. External validation was performed using data from Kim's Eye Hospital.

Results

The machine learning model was successfully trained using the data collected without coding. The random forest showed mean absolute errors of 124.8 µm and 152.4 µm for the internal 10-fold cross-validation and the external validation, respectively. For high vault prediction (>750 µm), the random forest showed areas under the curve of 0.725 and 0.760 for the internal and external validation datasets, respectively. The developed model performed better than the classic statistical regression models and the Google no-code platform.

Conclusions

Applying a no-code machine learning tool to our ICL implantation datasets showed a more accurate prediction of the postoperative vault than the classic regression and Google no-code models.

Translational Relevance

Because of significant bias in measurements and surgery between clinics, the no-code development of a customized machine learning nomogram will improve the accuracy of ICL implantation.

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.

Enhancing Vault Prediction and ICL Sizing Through Advanced Machine Learning Models

PURPOSE

To use artificial intelligence (AI) technology to accurately predict vault and Implantable Collamer Lens (ICL) size.

METHODS

The methodology focused on enhancing predictive capabilities through the fusion of machine-learning algorithms. Specifically, AdaBoost, Random Forest, Decision Tree, Support Vector Regression, LightGBM, and XGBoost were integrated into a majority-vote model. The performance of each model was evaluated using appropriate metrics such as accuracy, precision, F1-score, and area under the curve (AUC).

RESULTS

The majority-vote model exhibited the highest performance among the classification models, with an accuracy of 81.9% area under the curve (AUC) of 0.807. Notably, LightGBM (accuracy = 0.788, AUC = 0.803) and XGBoost (ACC = 0.790, AUC = 0.801) demonstrated competitive results. For the ICL size prediction, the Random Forest model achieved an impressive accuracy of 85.3% (AUC = 0.973), whereas XG-Boost (accuracy = 0.834, AUC = 0.961) and LightGBM (accuracy = 0.816, AUC = 0.961) maintained their compatibility.

CONCLUSIONS

This study highlights the potential of diverse machine learning algorithms to enhance postoperative vault and ICL size prediction, ultimately contributing to the safety of ICL implantation procedures. Furthermore, the introduction of the novel majority-vote model demonstrates its capability to combine the advantages of multiple models, yielding superior accuracy. Importantly, this study will empower ophthalmologists to use a precise tool for vault prediction, facilitating informed ICL size selection in clinical practice. [J Refract Surg. 2024;40(3):e126-e132.].

A review of posterior chamber phakic intraocular lenses

PURPOSE OF REVIEW

Posterior chamber phakic intraocular lenses (pIOLs) are increasing in popularity as a viable alternative to laser refractive surgery. The purpose of this review is to evaluate the recent updates to pIOLs and to assess the advancements and safety of the procedure.

RECENT FINDINGS

Accurate lens sizing is the key determinant to suitable vault prediction, advancements to sizing formulae including the use of very high frequency (VHF) digital ultrasound and the application of artificial intelligence and machine learning has led to improved vault prediction and safety. The introduction of the central aquaport has been shown to reduce the formation of cataract and is now adopted in most myopic pIOLs. Recently published studies have demonstrated that pIOLs have an excellent safety profile with no increased risk of retinal detachment or endothelial cell loss. Advancements have led to the introduction of extended depth of focus pIOLs for the correction of presbyopia, further research is required to evaluate the efficacy of new lens designs.

SUMMARY

pIOL surgery is experiencing traction with improved lens design and increased lenses choices such as larger optical zone and presbyopic options. Accuracy of implantable collamer lens sizing is paramount to the safety and clinical outcomes, greater predictability is likely to encourage more posterior chamber pIOL users due to fewer sizing related complications.

Clinical decision support system based on deep learning for evaluating implantable collamer lens size and vault after implantable collamer lens surgery: a retrospective study

OBJECTIVES

To aid doctors in selecting the optimal preoperative implantable collamer lens (ICL) size and to enhance the safety and surgical outcomes of ICL procedures, a clinical decision support system (CDSS) is proposed in our study.

DESIGN

A retrospective study of patients after ICL surgery.

SETTING

China Tertiary Myopia Prevention and Control Center.

PARTICIPANTS

2772 eyes belonging to 1512 patients after ICL surgery. Data were collected between 2018 and 2022.

OUTCOME MEASURES

A CDSS is constructed and used to predict vault at 1 month postoperatively and preoperative ICL dimensions using various artificial intelligence methods. Accuracy metrics as well as area under curve (AUC) parameters are used to determine the CDSS prediction methods.

RESULTS

Among the ICL size prediction models, conventional neural networks (CNNs) achieve the best prediction accuracy at 91.37% and exhibit the highest AUC of 0.842. Regarding the prediction model for vault values 1 month after surgery, CNN surpasses the other methods with an accuracy of 85.27%, which has the uppermost AUC of 0.815. Thus, we select CNN as the prediction algorithm for the CDSS.

CONCLUSIONS

This study introduces a CDSS to assist doctors in selecting the optimal ICL size for patients while improving the safety and postoperative outcomes of ICL surgery.

Choice of refractive surgery types for myopia assisted by machine learning based on doctors' surgical selection data

In recent years, corneal refractive surgery has been widely used in clinics as an effective means to restore vision and improve the quality of life. When choosing myopia-refractive surgery, it is necessary to comprehensively consider the differences in equipment and technology as well as the specificity of individual patients, which heavily depend on the experience of ophthalmologists. In our study, we took advantage of machine learning to learn about the experience of ophthalmologists in decision-making and assist them in the choice of corneal refractive surgery in a new case. Our study was based on the clinical data of 7,081 patients who underwent corneal refractive surgery between 2000 and 2017 at the Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences. Due to the long data period, there were data losses and errors in this dataset. First, we cleaned the data and deleted the samples of key data loss. Then, patients were divided into three groups according to the type of surgery, after which we used SMOTE technology to eliminate imbalance between groups. Six statistical machine learning models, including NBM, RF, AdaBoost, XGBoost, BP neural network, and DBN were selected, and a ten-fold cross-validation and grid search were used to determine the optimal hyperparameters for better performance. When tested on the dataset, the multi-class RF model showed the best performance, with agreement with ophthalmologist decisions as high as 0.8775 and Macro F1 as high as 0.8019. Furthermore, the results of the feature importance analysis based on the SHAP technique were consistent with an ophthalmologist's practical experience. Our research will assist ophthalmologists in choosing appropriate types of refractive surgery and will have beneficial clinical effects.

Predicting Implantable Collamer Lens Vault Using Machine Learning Based on Various Preoperative Biometric Factors

Purpose

To predict the vault size after Implantable Collamer Lens (ICL) V4c implantation using machine learning methods and to compare the predicted vault with the conventional manufacturer's nomogram.

Methods

This study included 707 patients (707 eyes) who underwent ICL V4c implantation at the Department of Ophthalmology, Peking Union Medical College Hospital, from September 2019 to January 2022. Random Forest Regression (RFR), XGBoost, and linear regression (LR) were used to predict the vault size 1 week after ICL V4c implantation. The mean absolute error (MAE), median absolute error (MedAE), root mean square error (RMSE), symmetric mean absolute percentage error (SMAPE), and Bland-Altman plot were utilized to compare the prediction performance of these machine learning methods.

Results

The dataset was divided into a training set of 180 patients (180 eyes) and a test set of 527 patients (527 eyes). XGBoost had the lowest prediction error, with mean MAE, RMSE, and SMAPE values of 121.70 µm, 148.87 µm, and 19.13%, respectively. The Bland‒Altman plots of RFR and XGBoost showed better prediction consistency than LR. However, XGBoost showed narrower 95% limits of agreement (LoA) than RFR, ranging from -307.12 to 256.59 µm.

Conclusions

XGBoost demonstrated better predictive performance than RFR and LR, as it had the lowest prediction error and the narrowest 95% LoA. Machine learning may be applicable for vault prediction, and it might be helpful for reducing the complications and the secondary surgery rate.

Translational Relevance

Using the proposed machine learning model, surgeons can consider the postoperative vault to reduce the surgical complications.

Effect of ciliary sulcus angle on the prediction of the vault for phakic implantable collamer lens in the KS formula

PURPOSE

We aimed to explore the effects of the ciliary sulcus angle (CSA) on accurate prediction of the vault after phakic implantable collamer lens (EVO ICL Model V4c) using the KS formula.

METHODS

Patients were classified according to the size of CSA: group A, narrow angle (CSA < 30°); group B, normal angle (CSA = 30-90°); and group C, wide angle (CSA > 90°). Further, differences between the actual vault dimensions at 3 months postoperatively and the preoperatively predicted vault dimensions in the three groups were analyzed.

RESULTS

This study included 223 eyes of 223 individuals. In groups A-C, the difference in the preoperative vault dimensions of the three groups predicted with the KS formula was not statistically significant (P = 0.056). The actual vault dimensions at 3 months postoperatively were significantly different between the three groups (P < 0.001). Moreover, the difference between the actual and predicted vaults by the KS formula was statistically significant (P < 0.001). In the 3 months, after surgery, the percentages of patients with a low vault (< 250 μm) were 0%, 3%, and 29% in groups A, B, and C, respectively. Further, the percentages of patients with an ideal vault (250-750 μm) in the postoperative period were 66%, 84%, and 71% in groups A, B, and C, respectively. Finally, the percentages of patients with a high vault (> 750 μm) in the postoperative period were 34%, 13%, and 0% in groups A, B, and C, respectively. Notably, the distribution of the vault among the three groups was statistically significant (P < 0.001).

CONCLUSION

The size of CSA significantly affects the predictiveness of the vault by the KS formula, with the most pronounced effect on the angles < 30° and > 90°. Therefore, CSA should be considered when selecting the lens size using the KS formula preoperatively.

CLINICAL TRIAL REGISTRATION NUMBER

ChiCTR2200065501.

Development and Validation of Data-Level Innovation Data-Balancing Machine Learning Models for Predicting Optimal Implantable Collamer Lens Size and Postoperative Vault

INTRODUCTION

There are only four sizes of implantable collamer lens (ICL) available for selection, which cannot completely fit all patients as a result of the discontinuity of ICL sizes. Sizing an optimal ICL and predicting postoperative vault are still unresolved problems. This study aimed to develop and validate innovative data-level data-balancing machine learning-based models for predicting ICL size and postoperative vault.

METHODS

The patients were randomly assigned to training and internal validation sets in a 4:1 ratio. Feature selection was performed using analysis of variance (ANOVA) and Kruskal-Wallis feature importance methods. Traditional linear regression model and machine learning-based models were used. The accuracy of models was assessed using the area under the curve (AUC) and confusion matrix.

RESULTS

A total of 564 patients (1127 eyes) were eligible for this study, consisting of 808 eyes in the training set, 202 eyes in the internal validation set, and 117 eyes in the external validation set. Compared with the traditional linear regression method, the machine learning model bagging tree showed the best performance for ICL size selection, with an accuracy of 84.5% (95% confidence interval (CI) 83.2-85.8%), and the AUC ranged from 0.88 to 0.99; the prediction accuracy of 12.1 mm and 13.7 mm ICL sizes was improved by 49% and 59%, respectively. The bagging tree model achieved the best accuracy [90.2%, (95% CI 88.9-91.5%)] for predicting the postoperative vault, and the AUC ranged from 0.90 to 0.94. The prediction accuracies of internal and external validation dataset for ICL sizing were 82.2% (95% CI 81.1-83.3%) and 82.1% (95% CI 81.1-83.1%), respectively.

CONCLUSIONS

The innovative data-level data balancing-based machine learning model can be used to predict ICL size and postoperative vault more accurately, which can assist surgeons in choosing optimal ICL size, thus reducing risks of postoperative complications and secondary surgery.

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.

Comparison of the Accuracy of Seven Vault Prediction Formulae for Implantable Collamer Lens Implantation

INTRODUCTION

This study aimed to compare the accuracy of seven implantable collamer lens (ICL) implantation vault prediction formulae.

METHODS

We retrospectively analyzed 328 patients (328 eyes) who underwent ICL implantation and the prediction accuracy of seven formulae: NK, KS, WH, Luo, Zhu, Hun, and ZZ were compared. Moreover, the accuracy of the seven formulae for different ICL sizes was compared. The formulae were tested using mean absolute prediction error (MAE), median absolute prediction error (MedAE), prediction error (PE) percentages at ± 50 µm, ± 100 µm, ± 200 µm, and ± 300 µm, and Bland-Altman analysis.

RESULTS

The PE of the seven formulae were statistically significant (P < 0.001). The KS (101.00 µm) and WH formulae (116.65 µm) had the smallest MedAE, followed by the Luo (123.62 µm), NK (141.50 µm), Hun (152.68 µm), ZZ (196.00 µm) and Zhu formula (225.98 µm). The highest percentage of PE in the range of ± 300µm was 94.3% and 93% for the KS and WH formulae, respectively. Among the different ICL size groupings, the KS formula predicted the smallest MedAE for 12.1 mm and 12.6 mm, whereas the Luo and WH formulae predicted the smallest MedAE for 13.2 mm and 13.7 mm, respectively.

CONCLUSIONS

The KS and WH formulae provided better outcomes by predicting the vault with higher accuracy than of the NK, Hun, Luo, ZZ, and Zhu formulae.

TRIAL REGISTRATION

ChiCTR2200065501.

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.

Evaluation of ciliary body morphology and position of the implantable collamer lens in low-vault eyes using ultrasound biomicroscopy

PURPOSE

To investigate the ciliary body anatomy and position of the implantable collamer lens (ICL) in low-vault eyes and analyze factors related to insufficient vault.

SETTING

Zhongshan Ophthalmic Center, Guangzhou, China.

DESIGN

Retrospective case-control observational study.

METHODS

In this study, 73 eyes of 73 patients with an insufficient vault (<250 μm) were matched with 73 eyes with an ideal vault (250 to 750 μm). Ultrasound biomicroscopy was used to determine the ciliary body morphology and ICL position. The biometric parameters acquired by Scheimpflug tomography were compared. The correlation between the vault and these factors was analyzed, and the least absolute shrinkage and selection operator method was used to screen the risk factors for low vault.

RESULTS

The low-vault group had a steeper corneal curvature, thicker lens thickness (LT), higher crystalline lens rise, and shorter axial length (AL) (all P < .005). The ciliary process length (CPL) and maximum ciliary body thickness (CBTmax) were significantly smaller, and the trabecular-ciliary angle (TCA), iris-ciliary angle (ICA), and ciliary sulcus width (CSW) were significantly greater in the low-vault eyes (all P < .005). The low-vault group had more ICL haptics below the ciliary process, and TCA, ICA, CPL, CBTmax, CSW, and haptic position were related to the postoperative vault (all P < .05). CPL, AL, and LT were identified as predictors of a low vault.

CONCLUSIONS

Malposition of ICL haptics behind the ciliary process is a risk factor for low vault. A shorter CPL, thicker LT, and shorter AL are significant risk factors for the postoperative low vault.

Vault predicting after implantable collamer lens implantation using random forest network based on different features in ultrasound biomicroscopy images

AIM

To analyze ultrasound biomicroscopy (UBM) images using random forest network to find new features to make predictions about vault after implantable collamer lens (ICL) implantation.

METHODS

A total of 450 UBM images were collected from the Lixiang Eye Hospital to provide the patient's preoperative parameters as well as the vault of the ICL after implantation. The vault was set as the prediction target, and the input elements were mainly ciliary sulcus shape parameters, which included 6 angular parameters, 2 area parameters, and 2 parameters, distance between ciliary sulci, and anterior chamber height. A random forest regression model was applied to predict the vault, with the number of base estimators (n_estimators) of 2000, the maximum tree depth (max_depth) of 17, the number of tree features (max_features) of Auto, and the random state (random_state) of 40.0.

RESULTS

Among the parameters selected in this study, the distance between ciliary sulci had a greater importance proportion, reaching 52% before parameter optimization is performed, and other features had less influence, with an importance proportion of about 5%. The importance of the distance between the ciliary sulci increased to 53% after parameter optimization, and the importance of angle 3 and area 1 increased to 5% and 8% respectively, while the importance of the other parameters remained unchanged, and the distance between the ciliary sulci was considered the most important feature. Other features, although they accounted for a relatively small proportion, also had an impact on the vault prediction. After parameter optimization, the best prediction results were obtained, with a predicted mean value of 763.688 µm and an actual mean value of 776.9304 µm. The R2 was 0.4456 and the root mean square error was 201.5166.

CONCLUSION

A study based on UBM images using random forest network can be performed for prediction of the vault after ICL implantation and can provide some reference for ICL size selection.

Artificial intelligence-aided diagnosis and treatment in the field of optometry

With the rapid development of computer technology, the application of artificial intelligence (AI) to ophthalmology has gained prominence in modern medicine. As modern optometry is closely related to ophthalmology, AI research on optometry has also increased. This review summarizes current AI research and technologies used for diagnosis in optometry, related to myopia, strabismus, amblyopia, optical glasses, contact lenses, and other aspects. The aim is to identify mature AI models that are suitable for research on optometry and potential algorithms that may be used in future clinical practice.

Vault Height Is a Key Predictive Factor for Anterior Segment Measurement Error by IOLMaster 700 in Eyes With Phakic Intraocular Lens

Purpose

To identify risk factors of ocular anterior segment measurement error by the IOLMaster 700 in eyes implanted with an implantable Collamer lens (ICL).

Methods

In total, 152 patients with clear lens (152 eyes, group 1) and another 32 cataract patients (57 eyes, group 2) who underwent ICL implantation were included, and the presence of measurement error by the IOLMaster 700 was determined based on B-scan images. The risk factors for measurement error were evaluated by logistic regression, and the optimal threshold was determined using receiver operating characteristic analysis.

Results

The ICL was misidentified as the anterior surface of the crystalline lens in 51.97% of eyes (79/152) in group 1 and 80.70% of eyes (46/57) in group 2. For every 100-µm decrease in the vault height, a 3.57- and 5.78-fold increase in the risk of measurement error was observed in group 1 and group 2, respectively. We identified an optimal threshold of the vault height at 389.47 µm for predicting biometric measurement error in eyes implanted with ICL, which showed an area under the curve of 0.93 (95% confidence interval, 0.90-0.97), a sensitivity of 0.87, and a specificity of 0.86.

Conclusions

Patients with ICL implantation, particularly those with a vault height less than 389.47 µm, are at a greater risk of anterior segment biometric measurement error by the IOLMaster 700.

Translational Relevance

The threshold of vault height can help to identify high-risk patients and further optimize biometric measurement.

A machine learning-based algorithm for estimating the original corneal curvature based on corneal topography after orthokeratology

OBJECTIVE

To estimate the original corneal curvature after orthokeratology by applying a machine learning-based algorithm.

METHODS

A total of 497 right eyes of 497 patients undergoing overnight orthokeratology for myopia for more than 1 year were enrolled in this retrospective study. All patients were fitted with lenses from Paragon CRT. Corneal topography was obtained by a Sirius corneal topography system (CSO, Italy). Original flat K (K1) and original steep K (K2) were set as the targets of calculation. The importance of each variable was explored by Fisher's criterion. Two machine learning models were established to allow adaptation to more situations. Bagging Tree, Gaussian process, support vector machine (SVM), and decision tree were used for prediction.

RESULTS

K2 after one year of orthokeratology (K2after) was most important in the prediction of K1 and K2. Bagging Tree performed best in both models 1 and 2 for K1 prediction (R = 0.812, RMSE = 0.855 in model 1 and R = 0.812, RMSE = 0.858 in model 2) and K2 prediction (R = 0.831, RMSE = 0.898 in model 1 and R = 0.837, RMSE = 0.888 in model 2). In model 1, the difference was 0.006 ± 1.34 D (p = 0.93) between the predictive value of K1 and the true value of K1 (K1before) and was 0.005 ± 1.51 D(p = 0.94) between the predictive value of K2 and the true value of K2 (K2before). In model 2, the difference was -0.056 ± 1.75 D (p = 0.59) between the predictive value of K1 and K1before and was 0.017 ± 2.01 D(p = 0.88) between the predictive value of K2 and K2before.

CONCLUSION

Bagging Tree performed best in predicting K1 and K2. Machine learning can be applied to predict the corneal curvature for those who cannot provide the initial corneal parameters in the outpatient clinic, providing a relatively certain degree of reference for the refitting of the Ortho-k lenses.

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.

Predictability of the vault after implantable collamer lens implantation using OCT and artificial intelligence in White patient eyes

PURPOSE

To compare the predicted vault using machine learning with the achieved vault using the online manufacturer's nomogram in patients undergoing posterior chamber implantation with an implantable collamer lens (ICL).

SETTING

Centro Oculistico Bresciano, Brescia, Italy, and I.R.C.C.S.-Bietti Foundation, Rome, Italy.

DESIGN

Retrospective multicenter comparison study.

METHODS

561 eyes from 300 consecutive patients who underwent ICL placement surgery were included in this study. All preoperative and postoperative measurements were obtained by anterior segment optical coherence tomography (AS-OCT; MS-39). The actual vault was quantitatively measured and compared with the predicted vault using machine learning of AS-OCT metrics.

RESULTS

A strong correlation between model predictions and achieved vaulting was detected by random forest regression (RF; R2 = 0.36), extra tree regression (ET; R2 = 0.50), and extreme gradient boosting regression ( R2 = 0.39). Conversely, a high residual difference was observed between achieved vaulting values and those predicted by the multilinear regression ( R2 = 0.33) and ridge regression ( R2 = 0.33). ET and RF regressions showed significantly lower mean absolute errors and higher percentages of eyes within ±250 μm of the intended ICL vault compared with the conventional nomogram (94%, 90%, and 72%, respectively; P < .001). ET classifiers achieved an accuracy (percentage of vault in the range of 250 to 750 μm) of up to 98%.

CONCLUSIONS

Machine learning of preoperative AS-OCT metrics achieved excellent predictability of ICL vault and size, which was significantly higher than the accuracy of the online manufacturer's nomogram, providing the surgeon with a valuable aid for predicting the ICL vault.

Predicting post-operative vault and optimal implantable collamer lens size using machine learning based on various ophthalmic device combinations

BACKGROUND

Implantable Collamer Lens (ICL) surgery has been proven to be a safe, effective, and predictable method for correcting myopia and myopic astigmatism. However, predicting the vault and ideal ICL size remains technically challenging. Despite the growing use of artificial intelligence (AI) in ophthalmology, no AI studies have provided available choices of different instruments and combinations for further vault and size predictions. This study aimed to fill this gap and predict post-operative vault and appropriate ICL size utilizing the comparison of numerous AI algorithms, stacking ensemble learning, and data from various ophthalmic devices and combinations.

RESULTS

This retrospective and cross-sectional study included 1941 eyes of 1941 patients from Zhongshan Ophthalmic Center. For both vault prediction and ICL size selection, the combination containing Pentacam, Sirius, and UBM demonstrated the best results in test sets [R² = 0.499 (95% CI 0.470-0.528), mean absolute error = 130.655 (95% CI 128.949-132.111), accuracy = 0.895 (95% CI 0.883-0.907), AUC = 0.928 (95% CI 0.916-0.941)]. Sulcus-to-sulcus (STS), a parameter from UBM, ranked among the top five significant contributors to both post-operative vault and optimal ICL size prediction, consistently outperforming white-to-white (WTW). Moreover, dual-device combinations or single-device parameters could also effectively predict vault and ideal ICL size, and excellent ICL selection prediction was achievable using only UBM parameters.

CONCLUSIONS

Strategies based on multiple machine learning algorithms for different ophthalmic devices and combinations are applicable for vault predicting and ICL sizing, potentially improving the safety of the ICL implantation. Moreover, our findings emphasize the crucial role of UBM in the perioperative period of ICL surgery, as it provides key STS measurements that outperformed WTW measurements in predicting post-operative vault and optimal ICL size, highlighting its potential to enhance ICL implantation safety and accuracy.

The Zhu-Lu formula: a machine learning-based intraocular lens power calculation formula for highly myopic eyes

BACKGROUND

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

METHODS

A total of 1828 eyes (from 1828 highly myopic patients) undergoing cataract surgery in our hospital were used as the internal dataset, and 151 eyes from 151 highly myopic patients from two other hospitals were used 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 Radial Basis Function (RBF) 3.0 formulas.

RESULTS

In the internal test dataset, the Zhu-Lu, RBF 3.0 and BUII ranked top three from low to high taking into account standard deviations (SDs) of prediction errors (PEs). The Zhu-Lu and RBF 3.0 showed significantly lower median absolute errors (MedAEs) than the other formulas (all P < 0.05). In the external test dataset, the Zhu-Lu, Kane and EVO 2.0 ranked top three from low to high 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 (all P < 0.05). The Zhu-Lu formula ranked first regarding the percentages of eyes within ± 0.50 D of the PE in both test datasets (internal: 80.61%; external: 72.85%). In the axial length subgroup analysis, the PE of the Zhu-Lu stayed stably close to zero in all subgroups.

CONCLUSIONS

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

Development and validation of a new multivariable prediction model to estimate risk of abnormal vault

PURPOSE

To develop and validate a new multivariable prediction model to estimate risk of abnormal vault after EVO Implantable Collamer Lens (EVO-ICL) implantation using the preoperative parameters.

METHODS

This retrospective study comprised 282 eyes of 143patients who underwent EVO-ICL surgery between May 2021 and April 2022. We measured preoperative parameters before surgery and vaults in 1 week after the operation using swept-source optical coherence tomography (SS-OCT). Risk factors for abnormal vault were determined by univariate and multivariate logistic regression analyses, and a nomogram was developed to forecast the risk of abnormal vault after EVO-ICL implantation. We assessed the performance of nomogram in terms of discrimination and calibration, including concordance index (C-index), receiver operating characteristic curve (ROC), area under the ROC curve (AUC), and decision curve analysis (DCA). Bootstrap resampling was used as an internal verification method.

RESULTS

The logistic regression analysis revealed the independent risk factors for abnormal vault were white-to-white(WTW), anterior chamber angle(ACA), pupil size, and ICL-size, all of them were used to establish a nomogram based on multivariate logistic regression to predict the risk of abnormal vault. The C-indexes and AUC were 0.669 (95%CI, 0.605, 0.733). The calibration curves of the nomogram showed relatively small bias from the reference line, implicating an acceptable degree of confidence. The DCA indicates the potential clinical significance of the nomogram.

CONCLUSIONS

We developed a new multivariable prediction model to estimate risk of abnormal vault. The model shows good prediction effect and can provide assistance for clinical decision of ICL size.

Artificial intelligence-based refractive error prediction and EVO-implantable collamer lens power calculation for myopia correction

BACKGROUND

Implantable collamer lens (ICL) has been widely accepted for its excellent visual outcomes for myopia correction. It is a new challenge in phakic IOL power calculation, especially for those with low and moderate myopia. This study aimed to establish a novel stacking machine learning (ML) model for predicting postoperative refraction errors and calculating EVO-ICL lens power.

METHODS

We enrolled 2767 eyes of 1678 patients (age: 27.5 ± 6.33 years, 18-54 years) who underwent non-toric (NT)-ICL or toric-ICL (TICL) implantation during 2014 to 2021. The postoperative spherical equivalent (SE) and sphere were predicted using stacking ML models [support vector regression (SVR), LASSO, random forest, and XGBoost] and training based on ocular dimensional parameters from NT-ICL and TICL cases, respectively. The accuracy of the stacking ML models was compared with that of the modified vergence formula (MVF) based on the mean absolute error (MAE), median absolute error (MedAE), and percentages of eyes within ± 0.25, ± 0.50, and ± 0.75 diopters (D) and Bland-Altman analyses. In addition, the recommended spheric lens power was calculated with 0.25 D intervals and targeting emmetropia.

RESULTS

After NT-ICL implantation, the random forest model demonstrated the lowest MAE (0.339 D) for predicting SE. Contrarily, the SVR model showed the lowest MAE (0.386 D) for predicting the sphere. After TICL implantation, the XGBoost model showed the lowest MAE for predicting both SE (0.325 D) and sphere (0.308 D). Compared with MVF, ML models had numerically lower values of standard deviation, MAE, and MedAE and comparable percentages of eyes within ± 0.25 D, ± 0.50 D, and ± 0.75 D prediction errors. The difference between MVF and ML models was larger in eyes with low-to-moderate myopia (preoperative SE >  - 6.00 D). Our final optimal stacking ML models showed strong agreement between the predictive values of MVF by Bland-Altman plots.

CONCLUSION

With various ocular dimensional parameters, ML models demonstrate comparable accuracy than existing MVF models and potential advantages in low-to-moderate myopia, and thus provide a novel nomogram for postoperative refractive error prediction and lens power calculation.

Artificial intelligence and digital solutions for myopia

Myopia as an uncorrected visual impairment is recognized as a global public health issue with an increasing burden on health-care systems. Moreover, high myopia increases one's risk of developing pathologic myopia, which can lead to irreversible visual impairment. Thus, increased resources are needed for the early identification of complications, timely intervention to prevent myopia progression, and treatment of complications. Emerging artificial intelligence (AI) and digital technologies may have the potential to tackle these unmet needs through automated detection for screening and risk stratification, individualized prediction, and prognostication of myopia progression. AI applications in myopia for children and adults have been developed for the detection, diagnosis, and prediction of progression. Novel AI technologies, including multimodal AI, explainable AI, federated learning, automated machine learning, and blockchain, may further improve prediction performance, safety, accessibility, and also circumvent concerns of explainability. Digital technology advancements include digital therapeutics, self-monitoring devices, virtual reality or augmented reality technology, and wearable devices - which provide possible avenues for monitoring myopia progression and control. However, there are challenges in the implementation of these technologies, which include requirements for specific infrastructure and resources, demonstrating clinically acceptable performance and safety of data management. Nonetheless, this remains an evolving field with the potential to address the growing global burden of myopia.

Artificial Intelligence in Ophthalmology - Status Quo and Future Perspectives

Artificial intelligence (AI) is an emerging technology in healthcare and holds the potential to disrupt many arms in medical care. In particular, disciplines using medical imaging modalities, including e.g. radiology but ophthalmology as well, are already confronted with a wide variety of AI implications. In ophthalmologic research, AI has demonstrated promising results limited to specific diseases and imaging tools, respectively. Yet, implementation of AI in clinical routine is not widely spread due to availability, heterogeneity in imaging techniques and AI methods. In order to describe the status quo, this narrational review provides a brief introduction to AI ("what the ophthalmologist needs to know"), followed by an overview of different AI-based applications in ophthalmology and a discussion on future challenges.Abbreviations: Age-related macular degeneration, AMD; Artificial intelligence, AI; Anterior segment OCT, AS-OCT; Coronary artery calcium score, CACS; Convolutional neural network, CNN; Deep convolutional neural network, DCNN; Diabetic retinopathy, DR; Machine learning, ML; Optical coherence tomography, OCT; Retinopathy of prematurity, ROP; Support vector machine, SVM; Thyroid-associated ophthalmopathy, TAO.

Development and validation of a routine blood parameters-based model for screening the occurrence of retinal detachment in high myopia in the context of PPPM

Background/aims

Timely detection and treatment of retinal detachment (RD) could effectively save vision and reduce the risk of progressing visual field defects. High myopia (HM) is known to be associated with an increased risk of RD. Evidently, it should be clearly discriminated the individuals with high or low risk of RD in patients with HM. By using multi-parametric analysis, risk assessment, and other techniques, it is crucial to create cutting-edge screening programs that may be utilized to improve population eye health and develop person-specific, cost-effective preventative, and targeted therapeutic measures. Therefore, we propose a novel, routine blood parameters-based prediction model as a screening program to help distinguish who should offer detailed ophthalmic examinations for RD diagnosis, prevent visual field defect progression, and provide personalized, serial monitoring in the context of predictive, preventive, and personalized medicine (PPPM/3 PM).

Methods

This population-based study included 20,870 subjects (HM = 19,284, HMRD = 1586) who underwent detailed routine blood tests and ophthalmic evaluations. HMRD cases and HM controls were matched using a nested case-control design. Then, the HMRD cases and HM controls were randomly assigned to the discovery cohort, validation cohort 1, and validation cohort 2 maintaining a 6:2:2 ratio, and other subjects were assigned to the HM validation cohort. Receiver operating characteristic curve analysis was performed to select feature indexes. Feature indexes were integrated into seven algorithm models, and an optimal model was selected based on the highest area under the curve (AUC) and accuracy.

Results

Six feature indexes were selected: lymphocyte, basophil, mean platelet volume, platelet distribution width, neutrophil-to-lymphocyte ratio, and lymphocyte-to-monocyte ratio. Among the algorithm models, the algorithm of conditional probability (ACP) showed the best performance achieving an AUC of 0.79, a diagnostic accuracy of 0.72, a sensitivity of 0.71, and a specificity of 0.74 in the discovery cohort. A good performance of the ACP model was also observed in the validation cohort 1 (AUC = 0.81, accuracy = 0.72, sensitivity = 0.71, specificity = 0.73) and validation cohort 2 (AUC = 0.77, accuracy = 0.71, sensitivity = 0.70, specificity = 0.72). In addition, ACP model calibration was found to be good across three cohorts. In the HM validation cohort, the ACP model achieved a diagnostic accuracy of 0.81 for negative classification.

Conclusion

We have developed a routine blood parameters-based model with an ACP algorithm that could potentially be applied in the clinic with a PPPM approach for serial monitoring and predicting the occurrence of RD in HM and can facilitate the prevention of HM progression to RD. According to the current study, routine blood measures are essential in patient risk classification, predictive diagnosis, and targeted therapy. Therefore, for high-risk RD persons, novel screening programs and prompt treatment plans are essential to enhance individual outcomes and healthcare offered to the community with HM.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-023-00319-3.

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.

Long-Term Vault Changes in Different Levels and Factors Affecting Vault Change After Implantation of Implantable Collamer Lens with a Central Hole

INTRODUCTION

This study evaluated vault changes in eyes implanted with an implantable Collamer lens (ICL) with a central hole (ICL V4c) for myopia and astigmatism correction as well as factors related to vault changes over time.

METHODS

This retrospective study enrolled 169 myopic eyes from 169 patients (137 women and 32 men) who underwent ICL V4c implantation to correct myopia and astigmatism. Vault values were measured quantitatively using a rotating Scheimpflug camera. Each patient underwent at least four postoperative follow-up visits at 1 month, 6 months, 1 year, and more than 2 years. We compared postoperative values between groups and identified factors affecting vault changes over time.

RESULTS

The mean vaults at 1 month (baseline), 6 months, 1 year, and the last follow-up time following ICL implantation were 540.83 ± 186.13, 520.00 ± 196.08, 503.79 ± 198.30, and 471.42 ± 211.35 μm, respectively. Eyes with baseline vaults of 250-750 and ≥ 750 μm exhibited a trend of vault decrease over time, and the differences were statistically significant (P < 0.05) at 6 months and 1 year postoperatively, respectively. The variables relevant to the value of vault decrease between baseline and last follow-up time were anterior chamber depth (ACD) and ICL power (adjusted R² = 0.121, P < 0.001).

CONCLUSIONS

We found a trend of decreased mean objective vault values over time, which was more obvious in eyes with higher baseline vault values. The vault value of the ICL decreased more in eyes with shallower ACDs, higher ICL power, or both. Moreover, the decrease in vault values became statistically significant earlier in eyes with higher baseline vaults or shallower ACDs.

Artificial intelligence technology for myopia challenges: A review

Myopia is a significant global health concern and affects human visual function, resulting in blurred vision at a distance. There are still many unsolved challenges in this field that require the help of new technologies. Currently, artificial intelligence (AI) technology is dominating medical image and data analysis and has been introduced to address challenges in the clinical practice of many ocular diseases. AI research in myopia is still in its early stages. Understanding the strengths and limitations of each AI method in specific tasks of myopia could be of great value and might help us to choose appropriate approaches for different tasks. This article reviews and elaborates on the technical details of AI methods applied for myopia risk prediction, screening and diagnosis, pathogenesis, and treatment.

Improvement in the ideal range of vault after implantable collamer lens implantation: a new vault prediction formula

Background

To derive and validate a novel vault prediction formula to improve the predictability and safety of implantable collamer lens (ICL) implantation.

Methods

Thirty-five patients (61 eyes) with previous posterior chamber intraocular lens implantation were included. Various parameters, such as horizontal-visible iris diameter (HVID), photopic pupil diameter (PPD), axial length (AL), white-to-white (WTW), anterior chamber width (ACW), angle-to-angle (ATA), crystalline lens rise (CLR), anterior chamber depth (ACD), horizontal sulcus-to-sulcus (HSTS), and ciliary sulcus angle (CSA) were measured. Vault was measured at 3 months after surgery using CASIA2 anterior segment optical coherence tomography. The formula was derived using multiple linear regression analysis and named as WH formula. It was validated in 65 patients (118 eyes) to determine the percentage of the ideal postoperative vault range and to compare the differences between the WH formula and the NK, KS, and STAAR formulas.

Results

Final ICL size, ATA, CSA, and CLR were included in the prediction formula model (adjusted R² = 0.67, p < 0.001). The achieved vault 1 month after the surgery was 556.19 μm ± 166.98 μm in the validation group, and the ideal vault range was 200-800 μm (92%). The difference between the achieved vault and that predicted using the WH formula was not statistically significant (p = 0.165), whereas the difference between the achieved vault and that predicted using the NK and KS formulas was statistically significant (p < 0.001 and p < 0.001, respectively). The 95% agreement limit range of the achieved vault and the vault predicted using the WH formula was narrower than those predicted using the NK and KS formulas (-295.20-258.82 μm).

Conclusion

This study combined the results of optical coherence tomography and ultrasound biomicroscopy measurements of the anterior segment of the eye and incorporated ciliary sulcus morphology quantification into the prediction formula. The study derived a prediction formula for vault by combining ICL size, ATA, and CLR. The derived formula was found to be superior to the currently available formulas.

Validation of the vault prediction model based on the sulcus-to-sulcus diameter and lens thickness: a 925-eye prospective study

BACKGROUND

To verify the accuracy and stability of the prediction formula based on the ciliary sulcus diameter and lens thickness and to analyse factors influencing the prediction results.

METHODS

In total, 925 eyes from 506 subjects were enrolled in this prospective study between July 1, 2020, and June 30, 2021. Subjects were divided into four seasons, each spanning three months. The target vault was set to be between 300 μm and 700 μm according the prediction formula. The actual vault was measured one month postoperatively. The Bland-Altman test, 95% confidence intervals (95% CI) and 95% limits of agreement (95% LoA) were used to evaluate the agreement between the predicted vault and the actual vault. Eyes with absolute prediction errors greater than 300 μm were further analysed.

RESULTS

The mean predicted vaults for the four seasons were 503 ± 99, 494 ± 96, 481 ± 92 and 502 ± 93 μm, while the mean actual vaults were 531 ± 189, 491 ± 179, 464 ± 179 and 529 ± 162 μm, respectively. The predicted and actual vaults of the overall subjects were 493 ± 95 and 500 ± 180 μm, respectively. Of the 925 eyes, 861 eyes (93.08%), 42 eyes (4.54%), and 22 eyes (2.38%) showed a normal vault, high vault, and low vault, respectively. Bland-Altman plots showed that the mean difference between the actual vault and predicted vault overall (± 95% LoA) was 6.43 ± 176.2 μm (-339 to 352 μm). Three UBM features may lead to large prediction errors (more than 300 μm): wide iris-ciliary angle (ICA), iris concavity and anteriorly positioned ciliary body.

CONCLUSIONS

This study demonstrated the accuracy and stability of the prediction formula through the validation of a large sample size and a long time span. Wide ICA, iris concavity and anteriorly positioned ciliary body may have an effect on vault.

Factors leading to realignment or exchange after implantable collamer lens implantation in 10 258 eyes

PURPOSE

To evaluate the incidence, causes, and outcomes of implantable collamer lens (ICL) realignment or exchange after implantation of the EVO-ICL.

SETTING

Eye and ENT Hospital of Fudan University, China.

DESIGN

Retrospective study.

METHODS

The study included 10 258 consecutive eyes after ICL implantation. Preoperative refractive and biometric measurements were compared between eyes with and without realignment or exchange. For eyes with ICL realignment or exchange, visual and biometric outcomes were also compared before and after ICL realignment or exchange.

RESULTS

The overall incidence of ICL realignment or exchange was 0.21% 22 eyes. 12 eyes (0.12%) underwent ICL realignment by axis rotation (10 eyes) or ICL exchange (2 eyes) due to toric ICL (TICL) misalignment. After realignment, uncorrected distance visual acuity improved, and residual cylinder decreased from -1.75 ± 0.48 diopters (D) to -0.87 ± 0.59 D ( P = .01). 10 eyes (0.10%) underwent vertical rotation of ICL (3 eyes) or ICL exchange (7 eyes) due to excessive vault. After either vertical rotation or ICL exchange, vault decreased significantly ( P < .05).

CONCLUSIONS

The incidence of ICL realignment or exchange after ICL implantation is low. TICL misalignment and excessive vault are 2 main causes. Implant exchange may be performed for excessive vault or misalignment with an insufficient vault. In addition, vertical rotation of an ICL may be a less invasive method to treat excessive vault in certain cases.