Comparison of Machine and Human Expert Evaluation of Capsulorrhexis Creation Performance Through Analysis of Surgical Video Recordings.

Purpose: Achieving competency in cataract surgery is an essential component of ophthalmology residency training. Video-based analysis of surgery can change training through its objective, reliable, and timely assessment of resident performance. Methods: Using the Image Labeler application in MATLAB, the capsulorrhexis step of 208 surgical videos, recorded at the University of Michigan, was annotated for subjective and objective analysis. Two expert surgeons graded the creation of the capsulorrhexis based on the International Council of Ophthalmology's Ophthalmology Surgical Competency Assessment Rubric:Phacoemulsification (ICO-OSCAR:phaco) rating scale and a custom rubric (eccentricity, roundness, size, centration) that focuses on the objective aspects of this step. The annotated rhexis frames were run through an automated analysis to obtain objective scores for these components. The subjective scores were compared using both intra and inter-rater analyses to assess the consistency of a human-graded scale. The subjective and objective scores were compared using intraclass correlation methods to determine relative agreement. Results: All rhexes were graded as 4/5 or 5/5 by both raters for both items 4 and 5 of the ICO-OSCAR:phaco rating scale. Only roundness scores were statistically different between the subjective graders (mean difference = -0.149, p-value = 0.0023). Subjective scores were highly correlated for all components (>0.6). Correlations between objective and subjective scores were low (0.09 to 0.39). Conclusion: Video-based analysis of cataract surgery presents significant opportunities, including the ability to asynchronously evaluate performance and provide longitudinal assessment. Subjective scoring between two raters was moderately correlated for each component.

Development of Crystalline Corneal Opacities (Steroid Keratopathy) in Dogs After Treatment With Ophthalmic Corticosteroids.

PURPOSE: To retrospectively evaluate and describe the relationship between the use of topical corticosteroids and the development of crystalline corneal opacities (steroid keratopathy) in a colony of research Beagles and Beagle-derived dogs. METHODS: Medical records of 73 purpose-bred Beagles and Beagle-derived dogs were reviewed from June 2012 to May 2021. All dogs were treated with topical ophthalmic corticosteroids for at least 21 days. In addition to regular ophthalmic examination, some dogs also had a systemic lipid profile (n = 6) performed to work up further and characterize the crystalline corneal opacities. Globes of 3 dogs were examined histopathologically. RESULTS: Axial stromal crystalline corneal opacities were appreciated in 25 eyes of 14 dogs after a median of 141 days after initiating treatment (35-396 days). Multiple corticosteroids were used, including neomycin-polymyxin b-dexamethasone 0.1% ophthalmic ointment, prednisolone acetate 1% ophthalmic suspension, and difluprednate 0.05% ophthalmic emulsion (Durezol). Resolution of corneal opacity was documented in 4 of 25 eyes when ophthalmic corticosteroids were discontinued after a median of 406.5 days (271-416 days). Histopathologic examination revealed a dense band of acellular material, poorly staining with periodic acid-Schiff, subtending the corneal epithelium, and being surrounded by spindle cells. CONCLUSIONS: This case series documents the onset of steroid keratopathy in Beagles and Beagle-derived dogs after treatment with ophthalmic corticosteroids. Clinical resolution of steroid keratopathy lesions may be possible after discontinuation of ophthalmic corticosteroids.

Evaluation of Methods for Detection and Semantic Segmentation of the Anterior Capsulotomy in Cataract Surgery Video.

Background: The capsulorhexis is one of the most important and challenging maneuvers in cataract surgery. Automated analysis of the anterior capsulotomy could aid surgical training through the provision of objective feedback and guidance to trainees. Purpose: To develop and evaluate a deep learning-based system for the automated identification and semantic segmentation of the anterior capsulotomy in cataract surgery video. Methods: In this study, we established a BigCat-Capsulotomy dataset comprising 1556 video frames extracted from 190 recorded cataract surgery videos for developing and validating the capsulotomy recognition system. The proposed system involves three primary stages: video preprocessing, capsulotomy video frame classification, and capsulotomy segmentation. To thoroughly evaluate its efficacy, we examined the performance of a total of eight deep learning-based classification models and eleven segmentation models, assessing both accuracy and time consumption. Furthermore, we delved into the factors influencing system performance by deploying it across various surgical phases. Results: The ResNet-152 model employed in the classification step of the proposed capsulotomy recognition system attained strong performance with an overall Dice coefficient of 92.21%. Similarly, the UNet model with the DenseNet-169 backbone emerged as the most effective segmentation model among those investigated, achieving an overall Dice coefficient of 92.12%. Moreover, the time consumption of the system was low at 103.37 milliseconds per frame, facilitating its application in real-time scenarios. Phase-wise analysis indicated that the Phacoemulsification phase (nuclear disassembly) was the most challenging to segment (Dice coefficient of 86.02%). Conclusion: The experimental results showed that the proposed system is highly effective in intraoperative capsulotomy recognition during cataract surgery and demonstrates both high accuracy and real-time capabilities. This system holds significant potential for applications in surgical performance analysis, education, and intraoperative guidance systems.

Severe Spontaneous Tilt of Scleral-Fixated Intraocular Lenses.

PURPOSE: To report and evaluate a multicenter series of 18 cases of severe, spontaneous IOL tilt involving the flanged intrascleral haptic fixation technique (FISHF). DESIGN: Clinical study with historical controls. METHODS: We report a cross-sectional study of 46 FISHF cases using the CT Lucia 602 IOL at a single academic center over a period of 24 weeks to determine the incidence of severe rotisserie-style rotational tilt. These rates were then compared with the same time-frame the prior year to help determine if this is a new phenomenon. Additional cases of severe tilt were solicited from another 4 academic centers. RESULTS: Among 46 FISHF cases at a single center, 5 developed severe tilt. No clear pattern in surgical technique, ocular history, or ocular anatomy was evident in these cases compared with controls, although the involved IOLs clustered within a narrow diopter range, indicative of a batch effect. In the same 24-week interval the year before, 33 FISHF cases were performed, none of which exhibited severe rotational tilt. In our multicenter dataset, 18 cases of tilt were identified. Surgeons included fellow and early-career physicians as well as surgeons with multiple years of experience with the Yamane technique. A variety of surgical approaches for FISHF were represented. In at least 8 of the cases, haptic rotation and/or dehiscence at the optic-haptic junction were documented. CONCLUSIONS: The identification of haptic rotation and dehiscence intraoperatively in several cases may reflect a new stability issue involving the optic-haptic junction.

Neovascularization against autologous SLET donor grafts despite successful corneal epithelialization and graft adherence.

PURPOSE: To report a case of neovascularization against autologous grafts after simple limbal epithelial transplantation (SLET) despite successful corneal epithelialization, as well as its subsequent regression without intervention. METHODS: A case report and review of the literature. RESULTS: A 52-year-old woman underwent uncomplicated autologous SLET for asymmetric limbal stem cell deficiency (LSCD) in the left eye. One month after the surgery, the patient had successful adherence of the graft and corneal epithelialization; however, new neovascularization developed in the left eye towards the graft sites. With only a slow taper of topical prednisolone acetate and polymyxin b/trimethoprim, the neovascularization regressed to ghost vessels over the following three months with improvement of her LSCD symptoms and increased clarity of her cornea. CONCLUSION: The limbus does not enjoy relative immune privilege like other parts of the eye; therefore, autologous limbal stem cell transplantation (along with the minimal immune response generated) is valuable for restoration of the ocular surface. Here, we describe neovascularization against autologous donor grafts despite an otherwise uncomplicated surgery and expected epithelialization course. Inflammation-mediated angiogenesis likely initiated the neovascularization, suggesting that immune mediators of inflammation may be inadvertently part of the graft tissue in bilateral LSCD.

Automatic Classification of Slit-Lamp Photographs by Imaging Illumination.

PURPOSE: The aim of this study was to facilitate deep learning systems in image annotations for diagnosing keratitis type by developing an automated algorithm to classify slit-lamp photographs (SLPs) based on illumination technique. METHODS: SLPs were collected from patients with corneal ulcer at Kellogg Eye Center, Bascom Palmer Eye Institute, and Aravind Eye Care Systems. Illumination techniques were slit beam, diffuse white light, diffuse blue light with fluorescein, and sclerotic scatter (ScS). Images were manually labeled for illumination and randomly split into training, validation, and testing data sets (70%:15%:15%). Classification algorithms including MobileNetV2, ResNet50, LeNet, AlexNet, multilayer perceptron, and k-nearest neighborhood were trained to distinguish 4 type of illumination techniques. The algorithm performances on the test data set were evaluated with 95% confidence intervals (CIs) for accuracy, F1 score, and area under the receiver operator characteristics curve (AUC-ROC), overall and by class (one-vs-rest). RESULTS: A total of 12,132 images from 409 patients were analyzed, including 41.8% (n = 5069) slit-beam photographs, 21.2% (2571) diffuse white light, 19.5% (2364) diffuse blue light, and 17.5% (2128) ScS. MobileNetV2 achieved the highest overall F1 score of 97.95% (CI, 97.94%-97.97%), AUC-ROC of 99.83% (99.72%-99.9%), and accuracy of 98.98% (98.97%-98.98%). The F1 scores for slit beam, diffuse white light, diffuse blue light, and ScS were 97.82% (97.80%-97.84%), 96.62% (96.58%-96.66%), 99.88% (99.87%-99.89%), and 97.59% (97.55%-97.62%), respectively. Slit beam and ScS were the 2 most frequently misclassified illumination. CONCLUSIONS: MobileNetV2 accurately labeled illumination of SLPs using a large data set of corneal images. Effective, automatic classification of SLPs is key to integrating deep learning systems for clinical decision support into practice workflows.

Adaptive Tensor-Based Feature Extraction for Pupil Segmentation in Cataract Surgery.

Cataract surgery remains the only definitive treatment for visually significant cataracts, which are a major cause of preventable blindness worldwide. Successful performance of cataract surgery relies on stable dilation of the pupil. Automated pupil segmentation from surgical videos can assist surgeons in detecting risk factors for pupillary instability prior to the development of surgical complications. However, surgical illumination variations, surgical instrument obstruction, and lens material hydration during cataract surgery can limit pupil segmentation accuracy. To address these problems, we propose a novel method named adaptive wavelet tensor feature extraction (AWTFE). AWTFE is designed to enhance the accuracy of deep learning-powered pupil recognition systems. First, we represent the correlations among spatial information, color channels, and wavelet subbands by constructing a third-order tensor. We then utilize higher-order singular value decomposition to eliminate redundant information adaptively and estimate pupil feature information. We evaluated the proposed method by conducting experiments with state-of-the-art deep learning segmentation models on our BigCat dataset consisting of 5,700 annotated intraoperative images from 190 cataract surgeries and a public CaDIS dataset. The experimental results reveal that the AWTFE method effectively identifies features relevant to the pupil region and improved the overall performance of segmentation models by up to 2.26% (BigCat) and 3.31% (CaDIS). Incorporation of the AWTFE method led to statistically significant improvements in segmentation performance (P < 1.29 × 10-10 for each model) and yielded the highest-performing model overall (Dice coefficients of 94.74% and 96.71% for the BigCat and CaDIS datasets, respectively). In performance comparisons, the AWTFE consistently outperformed other feature extraction methods in enhancing model performance. In addition, the proposed AWTFE method significantly improved pupil recognition performance by up to 2.87% in particularly challenging phases of cataract surgery.

CatStep: Automated Cataract Surgical Phase Classification and Boundary Segmentation Leveraging Inflated 3D-Convolutional Neural Network Architectures and BigCat.

Objective: Accurate identification of surgical phases during cataract surgery is essential for improving surgical feedback and performance analysis. Time spent in each surgical phase is an indicator of performance, and segmenting out specific phases for further analysis can simplify providing both qualitative and quantitative feedback on surgical maneuvers. Study Design: Retrospective surgical video analysis. Subjects: One hundred ninety cataract surgical videos from the BigCat dataset (comprising nearly 4 million frames, each labeled with 1 of 11 nonoverlapping surgical phases). Methods: Four machine learning architectures were developed for segmentation of surgical phases. Models were trained using cataract surgical videos from the BigCat dataset. Main Outcome Measures: Models were evaluated using metrics applied to frame-by-frame output and, uniquely in this work, metrics applied to phase output. Results: The final model, CatStep, a combination of a temporally sensitive model (Inflated 3D Densenet) and a spatially sensitive model (Densenet169), achieved an F1-score of 0.91 and area under the receiver operating characteristic curve of 0.95. Phase-level metrics showed considerable boundary segmentation performance with a median absolute error of phase start and end time of just 0.3 seconds and 0.1 seconds, respectively, a segmental F1-score @70 of 0.94, an oversegmentation score of 0.89, and a segmental edit score of 0.92. Conclusion: This study demonstrates the feasibility of high-performance automated surgical phase identification for cataract surgery and highlights the potential for improved surgical feedback and performance analysis. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Tensor-based Feature Extraction for Pupil Recognition in Cataract Surgery.

Cataract surgery remains the definitive treatment for cataracts, which are a major cause of preventable blindness worldwide. Adequate and stable dilation of the pupil are necessary for the successful performance of cataract surgery. Pupillary instability is a known risk factor for cataract surgery complications, and the accurate segmentation of the pupil from surgical video streams can enable the analysis of intraoperative pupil changes in cataract surgery. However, pupil segmentation performance can suffer due to variations in surgical illumination, obscuration of the pupil with surgical instruments, and hydration of the lens material intraoperatively. To overcome these challenges, we present a novel method called tensor-based pupil feature extraction (TPFE) to improve the accuracy of pupil recognition systems. We analyzed the efficacy of this approach with experiments performed on a dataset of 4,560 intraoperative annotated images from 190 cataract surgeries in human patients. Our results indicate that TPFE can identify features relevant to pupil segmentation and that pupil segmentation with state-of-the-art deep learning models can be significantly improved with the TPFE method.

Optical Biometry Changes Throughout Childhood and Adolescence in Patients Wearing Ortho-K Lenses.

Background: Orthokeratology has been shown to suppress progressive myopia in some children. We examine the changes in optical biometry parameters in orthokeratology (Ortho-K) patients, in a retrospective longitudinal study at a tertiary eye care center in Ann Arbor, MI, USA. Methods: Optical biometry measurements obtained with the Lenstar LS 900 (Haag-Streit USA Inc, EyeSuite software version i9.1.0.0) were aggregated from 170 patients who had undergone Ortho-K for myopia correction between 5 and 20 years of age. Pre-intervention biometry measurements were compared with follow-up measurements done 6-18 months after initiation of Ortho-K. Linear mixed models were used to quantify associations in biometry changes with age of intervention allowing for correlation between measurements on two eyes of the same patient. Results: A total of 91 patients were included in the study. Axial length increased through the age of 15.7 ± 0.84 years for Ortho-K patients at our center. The growth curve in our Ortho-K population was comparable to previously published normal growth curves in Wuhan and Germany populations. Corneal thickness and keratometry decreased at a stable rate regardless of age of intervention (-7.9 µm, 95% CI [-10.2, -5.7], p < 0.001). Conclusion: In our population, Ortho-K did not appear to affect the overall trajectory of axial length progression when compared to normal growth curves, despite showing a previously described reduction in corneal thickness. As Ortho-K has been shown to have varying effects that differ from individual to individual, it continues to be important to reassess its effects on new populations to better understand its ideal uses.

MAEPI and CIR: New Metrics for Robust Evaluation of the Prediction Performance of AI-Based IOL Formulas.

Purpose: To develop a class of new metrics for evaluating the performance of intraocular lens power calculation formulas robust to issues that can arise with AI-based methods. Methods: The dataset consists of surgical information and biometry measurements of 6893 eyes of 5016 cataract patients who received Alcon SN60WF lenses at University of Michigan's Kellogg Eye Center. We designed two types of new metrics: the MAEPI (Mean Absolute Error in Prediction of Intraocular Lens [IOL]) and the CIR (Correct IOL Rate) and compared the new metrics with traditional metrics including the mean absolute error (MAE), median absolute error, and standard deviation. We evaluated the new metrics with simulation analysis, machine learning (ML) methods, as well as existing IOL formulas (Barrett Universal II, Haigis, Hoffer Q, Holladay 1, PearlDGS, and SRK/T). Results: Results of traditional metrics did not accurately reflect the performance of overfitted ML formulas. By contrast, MAEPI and CIR discriminated between accurate and inaccurate formulas. The standard IOL formulas received low MAEPI and high CIR, which were consistent with the results of the traditional metrics. Conclusions: MAEPI and CIR provide a more accurate reflection of the real-life performance of AI-based IOL formula than traditional metrics. They should be computed in conjunction with conventional metrics when evaluating the performance of new and existing IOL formulas. Translational Relevance: The proposed new metrics would help cataract patients avoid the risks caused by inaccurate AI-based formulas, whose true performance cannot be determined by traditional metrics.

Ray tracing intraocular lens calculation performance improved by AI-powered postoperative lens position prediction.

AIMS: To assess whether incorporating a machine learning (ML) method for accurate prediction of postoperative anterior chamber depth (ACD) improves cataract surgery refraction prediction performance of a commonly used ray tracing power calculation suite (OKULIX). METHODS AND ANALYSIS: A dataset of 4357 eyes of 4357 patients with cataract was gathered at the Kellogg Eye Center, University of Michigan. A previously developed machine learning (ML)-based method was used to predict the postoperative ACD based on preoperative biometry measured with the Lenstar LS900 optical biometer. Refraction predictions were computed with standard OKULIX postoperative ACD predictions and ML-based predictions of postoperative ACD. The performance of the ray tracing approach with and without ML-based ACD prediction was evaluated using mean absolute error (MAE) and median absolute error (MedAE) in refraction prediction as metrics. RESULTS: Replacing the standard OKULIX postoperative ACD with the ML-predicted ACD resulted in statistically significant reductions in both MAE (1.7% after zeroing mean error) and MedAE (2.1% after zeroing mean error). ML-predicted ACD substantially improved performance in eyes with short and long axial lengths (p<0.01). CONCLUSIONS: Using an ML-powered postoperative ACD prediction method improves the prediction accuracy of the OKULIX ray tracing suite by a clinically small but statistically significant amount, with the greatest effect seen in long eyes.

Evaluation of the Nallasamy formula: a stacking ensemble machine learning method for refraction prediction in cataract surgery.

AIMS: To develop a new intraocular lens power selection method with improved accuracy for general cataract patients receiving Alcon SN60WF lenses. METHODS AND ANALYSIS: A total of 5016 patients (6893 eyes) who underwent cataract surgery at University of Michigan's Kellogg Eye Center and received the Alcon SN60WF lens were included in the study. A machine learning-based method was developed using a training dataset of 4013 patients (5890 eyes), and evaluated on a testing dataset of 1003 patients (1003 eyes). The performance of our method was compared with that of Barrett Universal II, Emmetropia Verifying Optical (EVO), Haigis, Hoffer Q, Holladay 1, PearlDGS and SRK/T. RESULTS: Mean absolute error (MAE) of the Nallasamy formula in the testing dataset was 0.312 Dioptres and the median absolute error (MedAE) was 0.242 D. Performance of existing methods were as follows: Barrett Universal II MAE=0.328 D, MedAE=0.256 D; EVO MAE=0.322 D, MedAE=0.251 D; Haigis MAE=0.363 D, MedAE=0.289 D; Hoffer Q MAE=0.404 D, MedAE=0.331 D; Holladay 1 MAE=0.371 D, MedAE=0.298 D; PearlDGS MAE=0.329 D, MedAE=0.258 D; SRK/T MAE=0.376 D, MedAE=0.300 D. The Nallasamy formula performed significantly better than seven existing methods based on the paired Wilcoxon test with Bonferroni correction (p<0.05). CONCLUSIONS: The Nallasamy formula (available at https://lenscalc.com/) outperformed the seven other formulas studied on overall MAE, MedAE, and percentage of eyes within 0.5 D of prediction. Clinical significance may be primarily at the population level.

Analysis of Cataract Surgery Instrument Identification Performance of Convolutional and Recurrent Neural Network Ensembles Leveraging BigCat.

Purpose: To develop a method for accurate automated real-time identification of instruments in cataract surgery videos. Methods: Cataract surgery videos were collected at University of Michigan's Kellogg Eye Center between 2020 and 2021. Videos were annotated for the presence of instruments to aid in the development, validation, and testing of machine learning (ML) models for multiclass, multilabel instrument identification. Results: A new cataract surgery database, BigCat, was assembled, containing 190 videos with over 3.9 million annotated frames, the largest reported cataract surgery annotation database to date. Using a dense convolutional neural network (CNN) and a recursive averaging method, we were able to achieve a test F1 score of 0.9528 and test area under the receiver operator characteristic curve of 0.9985 for surgical instrument identification. These prove to be state-of-the-art results compared to previous works, while also only using a fraction of the model parameters of the previous architectures. Conclusions: Accurate automated surgical instrument identification is possible with lightweight CNNs and large datasets. Increasingly complex model architecture is not necessary to retain a well-performing model. Recurrent neural network architectures add additional complexity to a model and are unnecessary to attain state-of-the-art performance. Translational Relevance: Instrument identification in the operative field can be used for further applications such as evaluating surgical trainee skill level and developing early warning detection systems for use during surgery.

AI-powered effective lens position prediction improves the accuracy of existing lens formulas.

AIMS: To assess whether incorporating a machine learning (ML) method for accurate prediction of postoperative anterior chamber depth (ACD) improves the refraction prediction performance of existing intraocular lens (IOL) calculation formulas. METHODS: A dataset of 4806 patients with cataract was gathered at the Kellogg Eye Center, University of Michigan, and split into a training set (80% of patients, 5761 eyes) and a testing set (20% of patients, 961 eyes). A previously developed ML-based method was used to predict the postoperative ACD based on preoperative biometry. This ML-based postoperative ACD was integrated into new effective lens position (ELP) predictions using regression models to rescale the ML output for each of four existing formulas (Haigis, Hoffer Q, Holladay and SRK/T). The performance of the formulas with ML-modified ELP was compared using a testing dataset. Performance was measured by the mean absolute error (MAE) in refraction prediction. RESULTS: When the ELP was replaced with a linear combination of the original ELP and the ML-predicted ELP, the MAEs±SD (in Diopters) in the testing set were: 0.356±0.329 for Haigis, 0.352±0.319 for Hoffer Q, 0.371±0.336 for Holladay, and 0.361±0.331 for SRK/T which were significantly lower (p<0.05) than those of the original formulas: 0.373±0.328 for Haigis, 0.408±0.337 for Hoffer Q, 0.384±0.341 for Holladay and 0.394±0.351 for SRK/T. CONCLUSION: Using a more accurately predicted postoperative ACD significantly improves the prediction accuracy of four existing IOL power formulas.

Bilateral Anterior Subcapsular Cataract Development Following Initiation of Enfortumab Vedotin.

Enfortumab vedotin is an antibody-drug conjugate that was recently granted accelerated US Food and Drug Administration approval for the treatment of locally advanced or metastatic urothelial cancer. Early clinical trials identified blurry vision, increased lacrimation and other events associated with dry eye as potential side effects. We report a case of bilateral anterior subcapsular cataract development following initiation of enfortumab vedotin. Enfortumab vedotin is not previously known to cause cataract development or progression and, thus, our patient's presentation may reflect the first report of an undocumented adverse effect of this novel agent.

Descemet membrane endothelial keratoplasty in a patient with iris-fixated intraocular lens and prior radial keratotomy: a case report.

BACKGROUND: Anterior segment surgeries such as cataract surgery, intraocular lens (IOL) repositioning, and radial keratotomy (RK) may hasten endothelial dysfunction, particularly in the context of pre-existing Fuchs dystrophy, necessitating future corneal transplantation. CASE PRESENTATION: A 68-year-old woman with a history of RK with associated irregular astigmatism in both eyes and iris-fixated intraocular lens (IF-IOL) in the left eye presented with six months of decreased vision in the left eye. She was found to have Fuchs dystrophy and underwent DMEK surgery. She had an uncomplicated postoperative course, with uncorrected visual acuity improving to 20/20 three months after surgery. CONCLUSION: To our knowledge, this is the first reported case of a highly successful DMEK surgery in a patient with prior RK and IF-IOL.

Gender differences in refraction prediction error of five formulas for cataract surgery.

OBJECTIVES: To evaluate gender differences in optical biometry measurements and lens power calculations. METHODS: Eight thousand four hundred thirty-one eyes of five thousand five hundred nineteen patients who underwent cataract surgery at University of Michigan's Kellogg Eye Center were included in this retrospective study. Data including age, gender, optical biometry, postoperative refraction, implanted intraocular lens (IOL) power, and IOL formula refraction predictions were gathered and/or calculated utilizing the Sight Outcomes Research Collaborative (SOURCE) database and analyzed. RESULTS: There was a statistical difference between every optical biometry measure between genders. Despite lens constant optimization, mean signed prediction errors (SPEs) of modern IOL formulas differed significantly between genders, with predictions skewed more hyperopic for males and myopic for females for all 5 of the modern IOL formulas tested. Optimization of lens constants by gender significantly decreased prediction error for 2 of the 5 modern IOL formulas tested. CONCLUSIONS: Gender was found to be an independent predictor of refraction prediction error for all 5 formulas studied. Optimization of lens constants by gender can decrease refraction prediction error for certain modern IOL formulas.

AI-Powered Effective Lens Position Prediction Improves the Accuracy of Existing Lens Formulas.

AIMS: To assess whether incorporating a machine learning (ML) method for accurate prediction of postoperative anterior chamber depth (ACD) improves the refraction prediction performance of existing intraocular lens (IOL) calculation formulas. METHODS: A dataset of 4806 cataract patients were gathered at the Kellogg Eye Center, University of Michigan, and split into a training set (80% of patients, 5761 eyes) and a testing set (20% of patients, 961 eyes). A previously developed ML-based method was used to predict the postoperative ACD based on preoperative biometry. This ML-based postoperative ACD was integrated into new effective lens position (ELP) predictions using regression models to rescale the ML output for each of four existing formulas (Haigis, Hoffer Q, Holladay, and SRK/T). The performance of the formulas with ML-modified ELP was compared using a testing dataset. Performance was measured by the mean absolute error (MAE) in refraction prediction. RESULTS: When the ELP was replaced with a linear combination of the original ELP and the ML-predicted ELP, the MAEs ± SD (in Diopters) in the testing set were: 0.356 ± 0.329 for Haigis, 0.352 ± 0.319 for Hoffer Q, 0.371 ± 0.336 for Holladay, and 0.361 ± 0.331 for SRK/T which were significantly lower than those of the original formulas: 0.373 ± 0.328 for Haigis, 0.408 ± 0.337 for Hoffer Q, 0.384 ± 0.341 for Holladay, and 0.394 ± 0.351 for SRK/T. CONCLUSION: Using a more accurately predicted postoperative ACD significantly improves the prediction accuracy of four existing IOL power formulas.

Epithelial Plaque Formation Secondary to Recombinant Human Nerve Growth Factor.

PURPOSE: To report a case of corneal epithelial plaque formation associated with recombinant human nerve growth factor (cenegermin 0.002%; Oxervate, Dompe[Combining Acute Accent] US Inc., Boston, MA), an as-yet unreported adverse event. METHODS: A case report and review of literature. RESULTS: A 45-year-old woman presented with a nonhealing 3.25- × 4.25-mm corneal epithelial defect secondary to multifactorial neurotrophic keratitis in the right eye. The epithelial defect was resistant to maximal medical therapy, and so cenegermin 0.002% was initiated, resulting in resolution of the corneal epithelial defect. After 6.5 weeks of treatment, she developed an unusual corneal epithelial plaque, decreased visual acuity, and eye pain. Cenegermin was ceased, after which the lesion resolved, visual acuity improved, and eye pain resolved. CONCLUSIONS: Cenegermin 0.002% has emerged as a promising treatment for neurotrophic keratitis. Reported adverse events with this agent have been minor and typically not vision threatening. Here, we describe corneal epithelial plaque formation as a visually significant adverse event that resolved with cessation of cenegermin 0.002%. Although the underlying mechanism is unknown, clinicians should be alerted to the possibility of epithelial plaque formation in patients being treated with recombinant human nerve growth factor for neurotrophic keratitis.