Machine learning predicting myopic regression after corneal refractive surgery using preoperative data and fundus photography

Artificial intelligence in the diagnosis and management of refractive errors

Refractive error is among the leading causes of visual impairment globally. The diagnosis and management of refractive error has traditionally relied on comprehensive eye examinations by eye care professionals, but access to these specialized services has remained limited in many areas of the world. Given this, artificial intelligence (AI) has shown immense potential in transforming the diagnosis and management of refractive error. We review AI applications across various aspects of refractive error care - from axial length prediction using fundus images to risk stratification for myopia progression. AI algorithms can be trained to analyze clinical data to detect refractive error as well as predict associated risks of myopia progression. For treatments such as implantable collamer and orthokeratology lenses, AI models facilitate vault size prediction and optimal lens fitting with high accuracy. Furthermore, AI has demonstrated promise in optimizing surgical planning and outcomes for refractive procedures. Emerging digital technologies such as telehealth, smartphone applications, and virtual reality integrated with AI present novel avenues for refractive error screening. We discuss key challenges, including limited validation datasets, lack of data standardization, image quality issues, population heterogeneity, practical deployment, and ethical considerations regarding patient privacy that need to be addressed before widespread clinical implementation.

Epidemiological insights into complication and outcomes in corneal refractive surgery population: findings from KNHANES 2010-2012

PURPOSE

Epidemiological studies on corneal refractive surgery remain limited, particularly regarding complications such as dry eye disease and refractive error regression, which impact long-term visual outcomes and patient satisfaction. This study aimed to evaluate the demographic and clinical characteristics of individuals with a history of corneal refractive surgery using data from the Korean National Health and Nutrition Examination Survey (KNHANES) 2010-2012.

METHODS

This cross-sectional study included 595 participants with a self-reported history of corneal refractive surgery. Data on diagnosed dry eye disease, dry eye symptoms, and previous ocular surgeries were collected through structured questionnaires, while ophthalmologic examinations provided information on refractive errors, intraocular pressure, and other ocular conditions. Logistic regression analysis identified factors associated with dry eye disease and symptoms.

RESULTS

Dry eye disease and refractive error regression were frequently reported among individuals with a history of corneal refractive surgery. Among participants, 24.2% reported diagnosed dry eye disease, and 33.1% reported dry eye symptoms. Significant myopia (≤ -0.75 D) and significant astigmatism (≤ -0.75 D) were present in 49.4% and 39.7%, respectively. Using the timing of the last ophthalmologic examination as a proxy for time since surgery, results showed a progressive myopic shift in spherical refractive error over time, while the prevalence of dry eye disease and symptoms gradually declined. Female sex (OR = 1.76, 95% CI = 1.05-2.96) and prolonged sun exposure (> 5 h/day, OR = 2.47, 95% CI = 0.96-6.36) were associated with a higher likelihood of diagnosed dry eye disease, while a longer time since surgery was associated with decreased dry eye symptoms. Severe diseases such as cataracts (0.3%), glaucoma (0.5%), and surgically treated retinal disorders (0.2%) were rare.

CONCLUSIONS

This study provides epidemiological insights into associations between corneal refractive surgery and postoperative outcomes, highlighting dry eye disease and refractive error regression as prevalent findings, while observing that severe complications were rarely reported. Sex and sun exposure were identified as important risk factors for dry eye disease, warranting attention in preoperative counseling and postoperative care. These findings support the need for procedure-specific, longitudinal research to optimize patient outcomes and satisfaction.

Artificial intelligence applications in cataract and refractive surgeries

PURPOSE OF REVIEW

This review highlights the recent advancements in the applications of artificial intelligence within the field of cataract and refractive surgeries. Given the rapid evolution of artificial intelligence technologies, it is essential to provide an updated overview of the significant strides and emerging trends in this field.

RECENT FINDINGS

Key themes include artificial intelligence-assisted diagnostics and intraoperative support, image analysis for anterior segment surgeries, development of artificial intelligence-based diagnostic scores and calculators for early disease detection and treatment planning, and integration of generative artificial intelligence for patient education and postoperative monitoring.

SUMMARY

The impact of artificial intelligence on cataract and refractive surgeries is becoming increasingly evident through improved diagnostic accuracy, enhanced patient education, and streamlined clinical workflows. These advancements hold significant implications for clinical practice, promising more personalized patient care and facilitating early disease detection and intervention. Equally, the review also highlights the fact that only some of this work reaches the clinical stage, successful integration of which may benefit from our focus.

Factors affecting long-term myopic regression after corneal refractive surgery for civilian pilots in southwest China

BACKGROUND

The purpose of this study was to analyze myopic regression after corneal refractive surgery (CRS) in civilian pilots and to explore the factors that may cause long-term myopic regression.

METHODS

We included civilian pilots who had undergone CRS to correct their myopia and who had at least 5 years of follow-up. We collected retrospective data and completed eye examinations and a questionnaire to assess their eye habits.

RESULTS

A total of 236 eyes were evaluated in this study. 211 eyes had Intrastromal ablations (167 eyes had laser in situ keratomileusis, LASIK, 44 eyes had small incision lenticule extraction, SMILE) and 25 eyes had subepithelial ablations (15 eyes had laser epithelial keratomileusis, LASEK and 10 eyes had photorefractive keratectomy, PRK). The mean preoperative spherical equivalent (SE) was - 2.92 ± 1.11 D (range from - 1.00 to -5.00 D). A total of 56 eyes (23.6%) suffered from myopic regression after CRS. Comparisons of individual and eye characteristics between the regression and non-regression groups revealed statistically significant differences in age, cumulative flight time, postoperative SE (at 6 months and current), uncorrected visual acuity (UCVA), accommodative amplitude (AA), positive relative accommodation (PRA), postoperative period, types of CRS and eye habits. Generalized propensity score weighting (GPSW) was used to balance the distribution of covariates among different age levels, types of CRS, cumulative flying time, postoperative period and continuous near-work time. The results of GPS weighted logistic regression demonstrated that the associations between age and myopic regression, types of CRS and myopic regression, continuous near-work time and myopic regression were significant. Cumulative flying time and myopic regression, postoperative period and myopic regression were no significant. Specifically, the odds ratio (OR) for age was 1.151 (P = 0.022), and the OR for type of CRS was 2.769 (P < 0.001). The OR for continuous near-work time was 0.635 with a P value of 0.038.

CONCLUSIONS

This is the first report to analyze myopic regression after CRS in civilian pilots. Our study found that for each year increase in age, the risk of civilian pilots experiencing myopic regression was increased. Intrastromal ablations had a lower risk of long-term myopia regression than subepithelial ablations. There is a higher risk of myopic progression with continuous near-work time > 45 min and poor accommodative function may be related factors in this specific population.

Deep learning prediction of steep and flat corneal curvature using fundus photography in post-COVID telemedicine era

Recently, fundus photography (FP) is being increasingly used. Corneal curvature is an essential factor in refractive errors and is associated with several pathological corneal conditions. As FP-based examination systems have already been widely distributed, it would be helpful for telemedicine to extract information such as corneal curvature using FP. This study aims to develop a deep learning model based on FP for corneal curvature prediction by categorizing corneas into steep, regular, and flat groups. The EfficientNetB0 architecture with transfer learning was used to learn FP patterns to predict flat, regular, and steep corneas. In validation, the model achieved a multiclass accuracy of 0.727, a Matthews correlation coefficient of 0.519, and an unweighted Cohen's κ of 0.590. The areas under the receiver operating characteristic curves for binary prediction of flat and steep corneas were 0.863 and 0.848, respectively. The optic nerve and its peripheral areas were the main focus of the model. The developed algorithm shows that FP can potentially be used as an imaging modality to estimate corneal curvature in the post-COVID-19 era, whereby patients may benefit from the detection of abnormal corneal curvatures using FP in the telemedicine setting.

Prediction of multiclass surgical outcomes in glaucoma using multimodal deep learning based on free-text operative notes and structured EHR data

OBJECTIVE

Surgical outcome prediction is challenging but necessary for postoperative management. Current machine learning models utilize pre- and post-op data, excluding intraoperative information in surgical notes. Current models also usually predict binary outcomes even when surgeries have multiple outcomes that require different postoperative management. This study addresses these gaps by incorporating intraoperative information into multimodal models for multiclass glaucoma surgery outcome prediction.

MATERIALS AND METHODS

We developed and evaluated multimodal deep learning models for multiclass glaucoma trabeculectomy surgery outcomes using both structured EHR data and free-text operative notes. We compare those to baseline models that use structured EHR data exclusively, or neural network models that leverage only operative notes.

RESULTS

The multimodal neural network had the highest performance with a macro AUROC of 0.750 and F1 score of 0.583. It outperformed the baseline machine learning model with structured EHR data alone (macro AUROC of 0.712 and F1 score of 0.486). Additionally, the multimodal model achieved the highest recall (0.692) for hypotony surgical failure, while the surgical success group had the highest precision (0.884) and F1 score (0.775).

DISCUSSION

This study shows that operative notes are an important source of predictive information. The multimodal predictive model combining perioperative notes and structured pre- and post-op EHR data outperformed other models. Multiclass surgical outcome prediction can provide valuable insights for clinical decision-making.

CONCLUSIONS

Our results show the potential of deep learning models to enhance clinical decision-making for postoperative management. They can be applied to other specialties to improve surgical outcome predictions.

Insights into artificial intelligence in myopia management: from a data perspective

Given the high incidence and prevalence of myopia, the current healthcare system is struggling to handle the task of myopia management, which is worsened by home quarantine during the ongoing COVID-19 pandemic. The utilization of artificial intelligence (AI) in ophthalmology is thriving, yet not enough in myopia. AI can serve as a solution for the myopia pandemic, with application potential in early identification, risk stratification, progression prediction, and timely intervention. The datasets used for developing AI models are the foundation and determine the upper limit of performance. Data generated from clinical practice in managing myopia can be categorized into clinical data and imaging data, and different AI methods can be used for analysis. In this review, we comprehensively review the current application status of AI in myopia with an emphasis on data modalities used for developing AI models. We propose that establishing large public datasets with high quality, enhancing the model's capability of handling multimodal input, and exploring novel data modalities could be of great significance for the further application of AI for myopia.

Artificial Intelligence in Ophthalmic Surgery: Current Applications and Expectations

Artificial Intelligence (AI) has found rapidly growing applications in ophthalmology, achieving robust recognition and classification in most kind of ocular diseases. Ophthalmic surgery is one of the most delicate microsurgery, requiring high fineness and stability of surgeons. The massive demand of the AI assist ophthalmic surgery will constitute an important factor in boosting accelerate precision medicine. In clinical practice, it is instrumental to update and review the considerable evidence of the current AI technologies utilized in the investigation of ophthalmic surgery involved in both the progression and innovation of precision medicine. Bibliographic databases including PubMed and Google Scholar were searched using keywords such as "ophthalmic surgery", "surgical selection", "candidate screening", and "robot-assisted surgery" to find articles about AI technology published from 2018 to 2023. In addition to the Editorials and letters to the editor, all types of approaches are considered. In this paper, we will provide an up-to-date review of artificial intelligence in eye surgery, with a specific focus on its application to candidate screening, surgery selection, postoperative prediction, and real-time intraoperative guidance.

Myopia prediction for children and adolescents via time-aware deep learning

This is a retrospective analysis. Quantitative prediction of the children's and adolescents' spherical equivalent based on their variable-length historical vision records. From October 2019 to March 2022, we examined uncorrected visual acuity, sphere, astigmatism, axis, corneal curvature and axial length of 75,172 eyes from 37,586 children and adolescents aged 6-20 years in Chengdu, China. 80% samples consist of the training set, the 10% form the validation set and the remaining 10% form the testing set. Time-Aware Long Short-Term Memory was used to quantitatively predict the children's and adolescents' spherical equivalent within two and a half years. The mean absolute prediction error on the testing set was 0.103 ± 0.140 (D) for spherical equivalent, ranging from 0.040 ± 0.050 (D) to 0.187 ± 0.168 (D) if we consider different lengths of historical records and different prediction durations. Time-Aware Long Short-Term Memory was applied to captured the temporal features in irregularly sampled time series, which is more in line with the characteristics of real data and thus has higher applicability, and helps to identify the progression of myopia earlier. The overall error 0.103 (D) is much smaller than the criterion for clinically acceptable prediction, say 0.75 (D).

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.

Efficacy of a Deep Learning System for Screening Myopic Maculopathy Based on Color Fundus Photographs

INTRODUCTION

The maculopathy in highly myopic eyes is complex. Its clinical diagnosis is a huge workload and subjective. To simply and quickly classify pathologic myopia (PM), a deep learning algorithm was developed and assessed to screen myopic maculopathy lesions based on color fundus photographs.

METHODS

This study included 10,347 ocular fundus photographs from 7606 participants. Of these photographs, 8210 were used for training and validation, and 2137 for external testing. A deep learning algorithm was trained, validated, and externally tested to screen myopic maculopathy which was classified into four categories: normal or mild tessellated fundus, severe tessellated fundus, early-stage PM, and advanced-stage PM. The area under the precision-recall curve, the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and Cohen's kappa were calculated and compared with those of retina specialists.

RESULTS

In the validation data set, the model detected normal or mild tessellated fundus, severe tessellated fundus, early-stage PM, and advanced-stage PM with AUCs of 0.98, 0.95, 0.99, and 1.00, respectively; while in the external-testing data set of 2137 photographs, the model had AUCs of 0.99, 0.96, 0.98, and 1.00, respectively.

CONCLUSIONS

We developed a deep learning model for detection and classification of myopic maculopathy based on fundus photographs. Our model achieved high sensitivities, specificities, and reliable Cohen's kappa, compared with those of attending ophthalmologists.