Applying Machine Learning Techniques in Nomogram Prediction and Analysis for SMILE Treatment

Optimizing Refractive Outcomes of SMILE: Artificial Intelligence versus Conventional State-of-the-Art Nomograms

PURPOSE

AI (artificial intelligence)-based methodologies have become established tools for researchers and physicians in the entire field of ophthalmology. However, the potential of AI to optimize the refractive outcome of keratorefractive surgery by means of machine learning (ML)-based nomograms has not been exhausted yet. In this study, we wanted to comprehensively compare state-of-the-art conventional nomograms for Small-Incision-Lenticule-Extraction (SMILE) with a novel ML-based nomogram regarding both their spherical and astigmatic predictability.

METHODS

A total of 1,342 eyes were analyzed for creation of three different nomograms based on a linear model (LM), a generalized additive mixed model (GAMM) and an artificial-neuronal-network (ANN), respectively. A total of 16 patient- and treatment-related features were included. Each model was trained by 895 eyes and validated by the remaining 447 eyes. Predictability was assessed by the difference between attempted and achieved change in spherical equivalent (SE) and the difference between target induced astigmatism (TIA) and surgically induced astigmatism (SIA). The root mean squared error (RMSE) of each model was computed as a measure of overall model performance.

RESULTS

The RMSE of LM, GAMM and ANN were 0.355, 0.348 and 0.367 for the prediction of SE and 0.279, 0.278 and 0.290 for the astigmatic correction, respectively. By applying the created models, the theoretical yield of eyes within ±0.50 D of SE from target refraction improved from 82 to 83% (LM), 84% (GAMM) and 83% (ANN), respectively. Astigmatic outcomes showed an improvement of eyes within ±0.50 D from TIA from 90 to 93% (LM), 93% (GAMM) and 92% (ANN), respectively. Subjective manifest refraction was the single most influential covariate in all models.

CONCLUSION

Machine learning endorsed the validity of state-of-the-art linear and non-linear SMILE nomograms. However, improving the accuracy of subjective manifest refraction seems warranted for optimizing ±0.50 D SE predictability beyond an apparent methodological 90% limit.

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.

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.

Relationship between postoperative residual refractive error and preoperative corneal stiffness in small-incision lenticule extraction

PURPOSE

To explore the relationship between postoperative residual refractive error and preoperative corneal stiffness after small-incision lenticule extraction (SMILE).

SETTING

Hospital clinic.

DESIGN

Retrospective cohort study.

METHODS

Corneal stiffness was evaluated using the stress-strain index (SSI). Associations between postoperative spherical equivalent (SE) and corneal stiffness were determined using longitudinal regression analysis after adjustment for sex, age, preoperative SE, and other variables. The cohort was divided into halves to compare risk ratios for residual refraction in corneas with different SSI values. Low SSI values were defined as having less-stiff corneas and others as having stiffer corneas.

RESULTS

287 patients (287 eyes) were included. Greater undercorrection was found in less-stiff corneas across all follow-up timepoints (less-stiff corneas: 1 day: -0.36 ± 0.45 diopters [D], 1 month: -0.22 ± 0.36 D, and 3 months: -0.13 ± 0.15 D; stiffer corneas: -0.22 ± 0.37 D, -0.14 ± 0.35 D, and -0.05 ± 0.11 D, respectively). Postoperative refraction exhibited a mean 0.05 D undercorrection for every 0.1-unit decrease in the SSI after adjustment for variables. The SSI accounted for nearly 10% of the variance in refractive outcomes. Less-stiff corneas increased the risk ratio of postoperative absolute SE >0 D and ≥0.25 D by 2.242 (95% CI, 1.334-3.768) and 3.023 (95% CI, 1.466-6.233), respectively, compared with stiffer corneas.

CONCLUSIONS

Postoperative residual refractive error was associated with preoperative corneal stiffness. Patients with less-stiff corneas had a 2- to 3-fold increased risk of residual refractive error after SMILE. Preoperative analysis of corneal stiffness can help modify nomogram algorithms of surgery and improve the predictability of refractive outcomes.

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.

Investigation of Accuracy and Influence Factors of Predicting Lenticule Thickness in Small Incision Lenticule Extraction by Machine Learning Models

Small-incision lenticule extraction (SMILE) is a safe and effective surgical procedure for refractive correction. However, the nomogram from the VisuMax femtosecond laser system often overestimates the achieved lenticule thickness (LT), leading to inaccurate estimation of residual central corneal thickness in some patients. In order to improve the accuracy of predicting achieved LT, we used machine learning models to make predictions of LT and analyze the influencing factors of LT estimation in this study. We collected nine variables of 302 eyes and their LT results as input variables. The input variables included age, sex, mean K reading of anterior corneal surface, lenticule diameter, preoperative CCT, axial length, the eccentricity of the anterior corneal surface (E), diopter of spherical, and diopter of the cylinder. Multiple linear regression and several machine learning algorithms were employed in developing the models for predicting LT. According to the evaluation results, the Random Forest (RF) model achieved the highest performance in predicting the LT with an R² of 0.95 and found the importance of CCT and E in predicting LT. To validate the effectiveness of the RF model, we selected additional 50 eyes for testing. Results showed that the nomogram overestimated LT by 19.59% on average, while the RF model underestimated LT by -0.15%. In conclusion, this study can provide efficient technical support for the accurate estimation of LT in SMILE.

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.

Identification of ocular refraction based on deep learning algorithm as a novel retinoscopy method

BACKGROUND

The evaluation of refraction is indispensable in ophthalmic clinics, generally requiring a refractor or retinoscopy under cycloplegia. Retinal fundus photographs (RFPs) supply a wealth of information related to the human eye and might provide a promising approach that is more convenient and objective. Here, we aimed to develop and validate a fusion model-based deep learning system (FMDLS) to identify ocular refraction via RFPs and compare with the cycloplegic refraction. In this population-based comparative study, we retrospectively collected 11,973 RFPs from May 1, 2020 to November 20, 2021. The performance of the regression models for sphere and cylinder was evaluated using mean absolute error (MAE). The accuracy, sensitivity, specificity, area under the receiver operating characteristic curve, and F1-score were used to evaluate the classification model of the cylinder axis.

RESULTS

Overall, 7873 RFPs were retained for analysis. For sphere and cylinder, the MAE values between the FMDLS and cycloplegic refraction were 0.50 D and 0.31 D, representing an increase of 29.41% and 26.67%, respectively, when compared with the single models. The correlation coefficients (r) were 0.949 and 0.807, respectively. For axis analysis, the accuracy, specificity, sensitivity, and area under the curve value of the classification model were 0.89, 0.941, 0.882, and 0.814, respectively, and the F1-score was 0.88.

CONCLUSIONS

The FMDLS successfully identified the ocular refraction in sphere, cylinder, and axis, and showed good agreement with the cycloplegic refraction. The RFPs can provide not only comprehensive fundus information but also the refractive state of the eye, highlighting their potential clinical value.

Integration of Artificial Intelligence into the Approach for Diagnosis and Monitoring of Dry Eye Disease

Dry eye disease (DED) is one of the most common diseases worldwide that can lead to a significant impairment of quality of life. The diagnosis and treatment of the disease are often challenging because of the lack of correlation between the signs and symptoms, limited reliability of diagnostic tests, and absence of established consensus on the diagnostic criteria. The advancement of machine learning, particularly deep learning technology, has enabled the application of artificial intelligence (AI) in various anterior segment disorders, including DED. Currently, many studies have reported promising results of AI-based algorithms for the accurate diagnosis of DED and precise and reliable assessment of data obtained by imaging devices for DED. Thus, the integration of AI into clinical approaches for DED can enhance diagnostic and therapeutic performance. In this review, in addition to a brief summary of the application of AI in anterior segment diseases, we will provide an overview of studies regarding the application of AI in DED and discuss the recent advances in the integration of AI into the clinical approach for DED.

Influence of optical zone on myopic correction in small incision lenticule extraction: a short-term study

BACKGROUND

To evaluate the influence of preoperative optical zone on myopic correction in small incision lenticule extraction.

METHODS

In this retrospective clinical study, 581 eyes from 316 patients underwent SMILE were selected, including 117 eyes in the small optical zone group (range from 6.0 to 6.4 mm) and 464 eyes in the large optical zone group (range from 6.5 to 6.8 mm). The measurements included uncorrected distance visual acuity (UDVA), corrected distance visual acuity (CDVA), spherical, and cylinder were measured preoperatively and 3 months postoperatively. Propensity score match (PSM) analysis was performed with age, gender, eye (right/left), keratometry and preoperative spherical equivalent between two different groups. The influence of optical zones on postoperative refractive outcomes were evaluated using univariate regression analysis.

RESULTS

In total, 78 pairs of eyes were selected by PSM (match ratio 1:1). There were no differences in the age, gender, eye (right/left), keratometry or preoperative spherical equivalent between the small and large optical zone groups. However, the difference of postoperative spherical equivalent was significantly between groups. Patients with larger optical zones had a trend towards less undercorrection (P = 0.018). Univariate linear regression model analysis found that each millimeter larger optical zone resulted in 8.13% or 0.39D less undercorrection (P < 0.001). The dependency between the optical zones and postoperative spherical equivalent was significant in the higher preoperative myopia group (r = 0.281, P < 0.001), but not significant in the lower myopia group (r = 0.028, P = 0.702).

CONCLUSION

The diameter of optical zones would affect postoperative refractive outcomes in small incision lenticule extraction. This study indicated that larger optical zones induced less undercorrection, especially in patients with high myopia.

Prognostic Model and Nomogram Construction and Validation With an Autophagy-Related Gene Signature in Low-Grade Gliomas

Background: Autophagy plays a vital role in cancer development. However, the prognostic value of autophagy-related genes (ARGs) in low-grade gliomas (LGG) is unclear. This research aimed to investigate whether ARGs correlated with overall survival (OS) in LGG patients.

Methods: RNA-sequencing data were obtained from The Cancer Genome Atlas (TCGA) TARGET GTEx database. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes enrichment analysis of ARGs were performed by the “clusterprofile” R package. Cox regression with the wald χ² test was employed to identify prognostic significant ARGs. Next, the receiver operator characteristic curves were established to evaluate the feasibility of risk score (riskscore=h0(t)exp(∑j=1nCoefj×Xj)) and other clinical risk factors to predict prognosis. A nomogram was constructed. Correlations between clinical features and ARGs were further verified by a t-test or Kruskal–Wallis test. In addition, the correlations between autophagy and immune cells were assessed through the single-sample gene set enrichment analysis (ssGSEA) and tumor immune estimation resource database. Last, the prediction model was verified by LGG data downloaded from the Chinese Glioma Genome Atlas (CGGA) database.

Results: Overall, 35 DE-ARGs were identified. Functional enrichment analysis showed that these genes were mainly related to oxidative stress and regulation of autophagy. Nine ARGs (BAX, BIRC5, CFLAR, DIRAS3, GRID2, MAPK9, MYC, PTK6, and TP53) were significantly associated with OS. Age (Hazard ratio (HR) = 1.063, 95% CI: 1.046–1.080), grade (HR = 3.412, 95% CI: 2.164–5.379), histological type (HR = 0.556, 95% CI: 0.346–0.893), and risk score (HR = 1.135, 95% CI: 1.104–1.167) were independent prognostic risk factors (all p < 0.05). In addition, BIRC5, CFLAR, DIRAS3, TP53, and risk scores were found to correlate significantly with age and tumor grade (all p < 0.05). Immune cell enrichment analysis demonstrated that the types of immune cells and their expression levels in the high-risk group were significantly different from those in the low-risk group (all p < 0.05). A prognostic nomogram was constructed to predict 1-, 3-, and 5-year survival, and the prognostic value of sorted ARGs were verified in the CGGA database and clinical samples.

Conclusion: Our findings suggest that the 9 DE-ARGs’ risk score model could serve as diagnostic and prognostic biomarkers. The prognostic nomograms could be useful for individualized survival prediction and improved treatment strategies.

Applying Information Gain to Explore Factors Affecting Small-Incision Lenticule Extraction: A Multicenter Retrospective Study

Purpose

This retrospective study aimed to identify the key factors influencing postoperative refraction after small-incision lenticule extraction (SMILE) using information gain.

Methods

This study comprised 2,350 eyes of 1,200 patients who underwent SMILE using a Visumax 500-kHz femtosecond laser (Carl Zeiss Meditec AG) in three ophthalmic centers: Tianjin Eye Hospital (center A), Jinan Mingshui Eye Hospital (center B), and Qingdao Eye Hospital (center C). Anterior segment features, including corneal curvature and central corneal thickness (CCT), were obtained from Pentacam HR (Oculus, Wetzlar, Germany). Information gain was calculated to analyze the importance of features affecting postoperative refraction.

Results

Preoperative and postoperative mean spherical equivalent (SE) refraction were −5.00 (−6.13, −3.88) D and 0.00 (−0.25, 0.13) D, respectively. None of the patients lost more than two lines of corrected distance visual acuity. The safety index was 1.32 ± 0.24, 1.03 ± 0.08, and 1.13 ± 0.16 in centers A, B, and C, respectively. The efficacy index was 1.31 ± 0.25, 1.02 ± 0.08, and 1.13 ± 0.17 in centers A, B, and C, respectively. At least 95% of the eyes were within ±1.00 D of the attempted correction. Postoperative refraction was related to preoperative spherical diopter refraction (r = 0.369, p < 0.001), preoperative SE (r = 0.364, p < 0.001), maximum lenticule thickness (r = −0.311, p < 0.001), preoperative uncorrected distance visual acuity (r = 0.164, p < 0.001), residual stromal thickness (r = 0.139, p < 0.001), preoperative mean anterior corneal curvature (r = −0.127, p < 0.001), preoperative flattest anterior corneal curvature (r = −0.122, p < 0.001), nomogram (r = −0.100, p < 0.001) and preoperative CCT (r = −0.058, p = 0.005).

Conclusions

SMILE was considered a safe and effective procedure for correcting myopia. Based on information gain, postoperative refraction was influenced by preoperative mean anterior corneal curvature, CCT, refraction, and residual stromal thickness.

Applications of Artificial Intelligence in Myopia: Current and Future Directions

With the continuous development of computer technology, big data acquisition and imaging methods, the application of artificial intelligence (AI) in medical fields is expanding. The use of machine learning and deep learning in the diagnosis and treatment of ophthalmic diseases is becoming more widespread. As one of the main causes of visual impairment, myopia has a high global prevalence. Early screening or diagnosis of myopia, combined with other effective therapeutic interventions, is very important to maintain a patient's visual function and quality of life. Through the training of fundus photography, optical coherence tomography, and slit lamp images and through platforms provided by telemedicine, AI shows great application potential in the detection, diagnosis, progression prediction and treatment of myopia. In addition, AI models and wearable devices based on other forms of data also perform well in the behavioral intervention of myopia patients. Admittedly, there are still some challenges in the practical application of AI in myopia, such as the standardization of datasets; acceptance attitudes of users; and ethical, legal and regulatory issues. This paper reviews the clinical application status, potential challenges and future directions of AI in myopia and proposes that the establishment of an AI-integrated telemedicine platform will be a new direction for myopia management in the post-COVID-19 period.

Global Tendency and Frontiers of Research on Myopia From 1900 to 2020: A Bibliometrics Analysis

Background:

Myopia is one of the most common causes of vision impairment in children and adults and has become a public health priority with its growing prevalence worldwide. This study aims to identify and evaluate the global trends in myopia research of the past century and visualize the frontiers using bibliometric analysis.

Methods

The literature search was conducted on the Web of Science for myopia studies published between 1900 and 2020. Retrieved publications were analyzed in-depth by the annual publication number, prolific countries and institutions, core author and journal, and the number of citations through descriptive statistics. Collaboration networks and keywords burst were visualized by VOSviewer and CiteSpace. Myopia citation network was visualized using CitNetExplorer.

Results

In total, 11,172 publications on myopia were retrieved from 1900 to 2020, with most published by the United States. Saw SM, from the National University of Singapore, contributed the most publications and citations. Investigative Ophthalmology &amp; Visual Science was the journal with highest number of citations. Journal of Cataract and Refractive Surgery with the maximum number of publications. The top 10 cited papers mainly focused on the epidemiology of myopia. Previous research emphasized myopia-associated experimental animal models, while recent keywords include “SMILE” and “myopia control” with the stronger burst, indicating a shift of concern from etiology to therapy and coincided with the global increment of incidence. Document citation network was clustered into six groups: “prevalence and risk factors of myopia,” “surgical control of myopia,” “pathogenesis of myopia,” “optical interventions of myopia,” “myopia and glaucoma,” and “pathological myopia.”

Conclusions

Bibliometrics analysis in this study could help scholars comprehend global trends of myopia research frontiers better. Hundred years of myopia research were clustered into six groups, among which “prevalence and risk factors of myopia” and “surgical control of myopia” were the largest groups. With the increasing prevalence of myopia, interventions of myopia control are a potential research hotspot and pressing public health issue.

Artificial Intelligence in Cornea, Refractive Surgery, and Cataract: Basic Principles, Clinical Applications, and Future Directions

ABSTRACT

Corneal diseases, uncorrected refractive errors, and cataract represent the major causes of blindness globally. The number of refractive surgeries, either cornea- or lens-based, is also on the rise as the demand for perfect vision continues to increase. With the recent advancement and potential promises of artificial intelligence (AI) technologies demonstrated in the realm of ophthalmology, particularly retinal diseases and glaucoma, AI researchers and clinicians are now channeling their focus toward the less explored ophthalmic areas related to the anterior segment of the eye. Conditions that rely on anterior segment imaging modalities, including slit-lamp photography, anterior segment optical coherence tomography, corneal tomography, in vivo confocal microscopy and/or optical biometers, are the most commonly explored areas. These include infectious keratitis, keratoconus, corneal grafts, ocular surface pathologies, preoperative screening before refractive surgery, intraocular lens calculation, and automated refraction, among others. In this review, we aimed to provide a comprehensive update on the utilization of AI in anterior segment diseases, with particular emphasis on the recent advancement in the past few years. In addition, we demystify some of the basic principles and terminologies related to AI, particularly machine learning and deep learning, to help improve the understanding, research and clinical implementation of these AI technologies among the ophthalmologists and vision scientists. As we march toward the era of digital health, guidelines such as CONSORT-AI, SPIRIT-AI, and STARD-AI will play crucial roles in guiding and standardizing the conduct and reporting of AI-related trials, ultimately promoting their potential for clinical translation.

Influence of Preoperative Keratometry on Refractive Outcomes for Myopia Correction With Small Incision Lenticule Extraction

PURPOSE

To evaluate the effect of preoperative keratometry on refractive outcomes after small incision lenticule extraction (SMILE) for myopia.

METHODS

This retrospective study comprised 515 consecutive eyes that had SMILE to correct myopia. Pearson correlation and linear regression were used to determine the relationship between residual spherical equivalent and preoperative keratometry. The same analyses were repeated in the quartiles with the lowest and highest preoperative myopia.

RESULTS

Preoperatively, the mean spherical equivalent was -5.67 ± 1.87 diopters (D) (range: -1.63 to -9.75 D) and the mean keratometry was 43.10 ± 1.30 D (range: 38.90 to 47.00 D). Three months postoperatively, the mean spherical equivalent was -0.07 ± 0.18 D. After adjustment for age, sex, and preoperative spherical equivalent, greater postoperative undercorrection occurred in eyes with steeper corneas (P = .001). Each diopter of steeper keratometry resulted in 0.52% (0.03 D) more undercorrection. Correlation between the mean preoperative keratometry and residual spherical equivalent was significant in the lower preoperative myopia group (r = -0.24, P = .006), but not significant in the higher myopia group (r = -0.02, P = .809).

CONCLUSIONS

Preoperative keratometry affects refractive outcomes after SMILE. Steeper corneas have greater undercorrection, especially in eyes with low myopia. Knowledge of the correlation between refractive outcomes of SMILE and keratometry would help in modifying current treatment algorithms. [J Refract Surg. 2020;36(6):374-379.].

Artificial intelligence-based nomogram for small-incision lenticule extraction

BACKGROUND

Small-incision lenticule extraction (SMILE) is a surgical procedure for the refractive correction of myopia and astigmatism, which has been reported as safe and effective. However, over- and under-correction still occur after SMILE. The necessity of nomograms is emphasized to achieve optimal refractive results. Ophthalmologists diagnose nomograms by analyzing the preoperative refractive data with their individual knowledge which they accumulate over years of experience. Our aim was to predict the nomograms of sphere, cylinder, and astigmatism axis for SMILE accurately by applying machine learning algorithm.

METHODS

We retrospectively analyzed the data of 3,034 eyes composed of four categorical features and 28 numerical features selected from 46 features. The multiple linear regression, decision tree, AdaBoost, XGBoost, and multi-layer perceptron were employed in developing the nomogram models for sphere, cylinder, and astigmatism axis. The scores of the root-mean-square error (RMSE) and accuracy were evaluated and compared. Subsequently, the feature importance of the best models was calculated.

RESULTS

AdaBoost achieved the highest performance with RMSE of 0.1378, 0.1166, and 5.17 for the sphere, cylinder, and astigmatism axis, respectively. The accuracies of which error below 0.25 D for the sphere and cylinder nomograms and 25° for the astigmatism axis nomograms were 0.969, 0.976, and 0.994, respectively. The feature with the highest importance was preoperative manifest refraction for all the cases of nomograms. For the sphere and cylinder nomograms, the following highly important feature was the surgeon.

CONCLUSIONS

Among the diverse machine learning algorithms, AdaBoost exhibited the highest performance in the prediction of the sphere, cylinder, and astigmatism axis nomograms for SMILE. The study proved the feasibility of applying artificial intelligence (AI) to nomograms for SMILE. Also, it may enhance the quality of the surgical result of SMILE by providing assistance in nomograms and preventing the misdiagnosis in nomograms.

Application of Artificial Intelligence in the Diagnosis and Management of Corneal Diseases

Diagnosis and treatment planning in ophthalmology heavily depend on clinical examination and advanced imaging modalities, which can be time-consuming and carry the risk of human error. Artificial intelligence (AI) and deep learning (DL) are being used in different fields of ophthalmology and in particular, when running diagnostics and predicting outcomes of anterior segment surgeries. This review will evaluate the recent developments in AI for diagnostics, surgical interventions, and prognosis of corneal diseases. It also provides a brief overview of the newer AI dependent modalities in corneal diseases.

Advances in Imaging Technology of Anterior Segment of the Eye

Advances in imaging technology and computer science have allowed the development of newer assessment of the anterior segment, including Corvis ST, Brillouin microscopy, ultrahigh-resolution optical coherence tomography, and artificial intelligence. They enable accurate and precise assessment of structural and biomechanical alterations associated with anterior segment disorders. This review will focus on these 4 new techniques, and a brief overview of these modalities will be introduced. The authors will also discuss the recent advances in research regarding these techniques and potential application of these techniques in clinical practice. Many studies on these modalities have reported promising results, indicating the potential for more detailed comprehensive understanding of the anterior segment tissues.

Model-to-Data Approach for Deep Learning in Optical Coherence Tomography Intraretinal Fluid Segmentation

Importance

Amid an explosion of interest in deep learning in medicine, including within ophthalmology, concerns regarding data privacy, security, and sharing are of increasing importance. A model-to-data approach, in which the model itself is transferred rather than data, can circumvent many of these challenges but has not been previously demonstrated in ophthalmology.

Objective

To determine whether a model-to-data deep learning approach (ie, validation of the algorithm without any data transfer) can be applied in ophthalmology.

Design, Setting, and Participants

This single-center cross-sectional study included patients with active exudative age-related macular degeneration undergoing optical coherence tomography (OCT) at the New England Eye Center from August 1, 2018, to February 28, 2019. Data were primarily analyzed from March 1 to June 20, 2019.

Main Outcomes and Measures

Training of the deep learning model, using a model-to-data approach, in recognizing intraretinal fluid (IRF) on OCT B-scans.

Results

The model was trained (learning curve Dice coefficient, >80%) using 400 OCT B-scans from 128 participants (69 female [54%] and 59 male [46%]; mean [SD] age, 77.5 [9.1] years). In comparing the model with manual human grading of IRF pockets, no statistically significant difference in Dice coefficients or intersection over union scores was found (P > .05).

Conclusions and Relevance

A model-to-data approach to deep learning applied in ophthalmology avoided many of the traditional hurdles in large-scale deep learning, including data sharing, security, and privacy concerns. Although the clinical relevance of these results is limited at this time, this proof-of-concept study suggests that such a paradigm should be further examined in larger-scale, multicenter deep learning studies.

Artificial intelligence for anterior segment diseases: Emerging applications in ophthalmology

With the advancement of computational power, refinement of learning algorithms and architectures, and availability of big data, artificial intelligence (AI) technology, particularly with machine learning and deep learning, is paving the way for 'intelligent' healthcare systems. AI-related research in ophthalmology previously focused on the screening and diagnosis of posterior segment diseases, particularly diabetic retinopathy, age-related macular degeneration and glaucoma. There is now emerging evidence demonstrating the application of AI to the diagnosis and management of a variety of anterior segment conditions. In this review, we provide an overview of AI applications to the anterior segment addressing keratoconus, infectious keratitis, refractive surgery, corneal transplant, adult and paediatric cataracts, angle-closure glaucoma and iris tumour, and highlight important clinical considerations for adoption of AI technologies, potential integration with telemedicine and future directions.