Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children

A Competition for the Diagnosis of Myopic Maculopathy by Artificial Intelligence Algorithms

Importance

Myopic maculopathy (MM) is a major cause of vision impairment globally. Artificial intelligence (AI) and deep learning (DL) algorithms for detecting MM from fundus images could potentially improve diagnosis and assist screening in a variety of health care settings.

Objectives

To evaluate DL algorithms for MM classification and segmentation and compare their performance with that of ophthalmologists.

Design, Setting, and Participants

The Myopic Maculopathy Analysis Challenge (MMAC) was an international competition to develop automated solutions for 3 tasks: (1) MM classification, (2) segmentation of MM plus lesions, and (3) spherical equivalent (SE) prediction. Participants were provided 3 subdatasets containing 2306, 294, and 2003 fundus images, respectively, with which to build algorithms. A group of 5 ophthalmologists evaluated the same test sets for tasks 1 and 2 to ascertain performance. Results from model ensembles, which combined outcomes from multiple algorithms submitted by MMAC participants, were compared with each individual submitted algorithm. This study was conducted from March 1, 2023, to March 30, 2024, and data were analyzed from January 15, 2024, to March 30, 2024.

Exposure

DL algorithms submitted as part of the MMAC competition or ophthalmologist interpretation.

Main Outcomes and Measures

MM classification was evaluated by quadratic-weighted κ (QWK), F1 score, sensitivity, and specificity. MM plus lesions segmentation was evaluated by dice similarity coefficient (DSC), and SE prediction was evaluated by R2 and mean absolute error (MAE).

Results

The 3 tasks were completed by 7, 4, and 4 teams, respectively. MM classification algorithms achieved a QWK range of 0.866 to 0.901, an F1 score range of 0.675 to 0.781, a sensitivity range of 0.667 to 0.778, and a specificity range of 0.931 to 0.945. MM plus lesions segmentation algorithms achieved a DSC range of 0.664 to 0.687 for lacquer cracks (LC), 0.579 to 0.673 for choroidal neovascularization, and 0.768 to 0.841 for Fuchs spot (FS). SE prediction algorithms achieved an R2 range of 0.791 to 0.874 and an MAE range of 0.708 to 0.943. Model ensemble results achieved the best performance compared to each submitted algorithms, and the model ensemble outperformed ophthalmologists at MM classification in sensitivity (0.801; 95% CI, 0.764-0.840 vs 0.727; 95% CI, 0.684-0.768; P = .006) and specificity (0.946; 95% CI, 0.939-0.954 vs 0.933; 95% CI, 0.925-0.941; P = .009), LC segmentation (DSC, 0.698; 95% CI, 0.649-0.745 vs DSC, 0.570; 95% CI, 0.515-0.625; P < .001), and FS segmentation (DSC, 0.863; 95% CI, 0.831-0.888 vs DSC, 0.790; 95% CI, 0.742-0.830; P < .001).

Conclusions and Relevance

In this diagnostic study, 15 AI models for MM classification and segmentation on a public dataset made available for the MMAC competition were validated and evaluated, with some models achieving better diagnostic performance than ophthalmologists.

Artificial intelligence in myopia in children: current trends and future directions

PURPOSE OF REVIEW

Myopia is one of the major causes of visual impairment globally, with myopia and its complications thus placing a heavy healthcare and economic burden. With most cases of myopia developing during childhood, interventions to slow myopia progression are most effective when implemented early. To address this public health challenge, artificial intelligence has emerged as a potential solution in childhood myopia management.

RECENT FINDINGS

The bulk of artificial intelligence research in childhood myopia was previously focused on traditional machine learning models for the identification of children at high risk for myopia progression. Recently, there has been a surge of literature with larger datasets, more computational power, and more complex computation models, leveraging artificial intelligence for novel approaches including large-scale myopia screening using big data, multimodal data, and advancing imaging technology for myopia progression, and deep learning models for precision treatment.

SUMMARY

Artificial intelligence holds significant promise in transforming the field of childhood myopia management. Novel artificial intelligence modalities including automated machine learning, large language models, and federated learning could play an important role in the future by delivering precision medicine, improving health literacy, and allowing the preservation of data privacy. However, along with these advancements in technology come practical challenges including regulation and clinical integration.

Artificial intelligence in the anterior segment of eye diseases

Ophthalmology is a subject that highly depends on imaging examination. Artificial intelligence (AI) technology has great potential in medical imaging analysis, including image diagnosis, classification, grading, guiding treatment and evaluating prognosis. The combination of the two can realize mass screening of grass-roots eye health, making it possible to seek medical treatment in the mode of "first treatment at the grass-roots level, two-way referral, emergency and slow treatment, and linkage between the upper and lower levels". On the basis of summarizing the AI technology carried out by scholars and their teams all over the world in the field of ophthalmology, quite a lot of studies have confirmed that machine learning can assist in diagnosis, grading, providing optimal treatment plans and evaluating prognosis in corneal and conjunctival diseases, ametropia, lens diseases, glaucoma, iris diseases, etc. This paper systematically shows the application and progress of AI technology in common anterior segment ocular diseases, the current limitations, and prospects for the future.

A deep learning system for myopia onset prediction and intervention effectiveness evaluation in children

The increasing prevalence of myopia worldwide presents a significant public health challenge. A key strategy to combat myopia is with early detection and prediction in children as such examination allows for effective intervention using readily accessible imaging technique. To this end, we introduced DeepMyopia, an artificial intelligence (AI)-enabled decision support system to detect and predict myopia onset and facilitate targeted interventions for children at risk using routine retinal fundus images. Based on deep learning architecture, DeepMyopia had been trained and internally validated on a large cohort of retinal fundus images (n = 1,638,315) and then externally tested on datasets from seven sites in China (n = 22,060). Our results demonstrated robustness of DeepMyopia, with AUCs of 0.908, 0.813, and 0.810 for 1-, 2-, and 3-year myopia onset prediction with the internal test set, and AUCs of 0.796, 0.808, and 0.767 with the external test set. DeepMyopia also effectively stratified children into low- and high-risk groups (p < 0.001) in both test sets. In an emulated randomized controlled trial (eRCT) on the Shanghai outdoor cohort (n = 3303) where DeepMyopia showed effectiveness in myopia prevention compared to NonCyc-based model, with an adjusted relative reduction (ARR) of -17.8%, 95% CI: -29.4%, -6.4%. DeepMyopia-assisted interventions attained quality-adjusted life years (QALYs) of 0.75 (95% CI: 0.53, 1.04) per person and avoided blindness years of 13.54 (95% CI: 9.57, 18.83) per 1 million persons compared to natural lifestyle with no active intervention. Our findings demonstrated DeepMyopia as a reliable and efficient AI-based decision support system for intervention guidance for children.

Myopia Control: Are We Ready for an Evidence Based Approach?

INTRODUCTION

Myopia and its vision-threatening complications present a significant public health problem. This review aims to provide an updated overview of the multitude of known and emerging interventions to control myopia, including their potential effect, safety, and costs.

METHODS

A systematic literature search of three databases was conducted. Interventions were grouped into four categories: environmental/behavioral (outdoor time, near work), pharmacological (e.g., atropine), optical interventions (spectacles and contact lenses), and novel approaches such as red-light (RLRL) therapies. Review articles and original articles on randomized controlled trials (RCT) were selected.

RESULTS

From the initial 3224 retrieved records, 18 reviews and 41 original articles reporting results from RCTs were included. While there is more evidence supporting the efficacy of low-dose atropine and certain myopia-controlling contact lenses in slowing myopia progression, the evidence about the efficacy of the newer interventions, such as spectacle lenses (e.g., defocus incorporated multiple segments and highly aspheric lenslets) is more limited. Behavioral interventions, i.e., increased outdoor time, seem effective for preventing the onset of myopia if implemented successfully in schools and homes. While environmental interventions and spectacles are regarded as generally safe, pharmacological interventions, contact lenses, and RLRL may be associated with adverse effects. All interventions, except for behavioral change, are tied to moderate to high expenditures.

CONCLUSION

Our review suggests that myopia control interventions are recommended and prescribed on the basis of accessibility and clinical practice patterns, which vary widely around the world. Clinical trials indicate short- to medium-term efficacy in reducing myopia progression for various interventions, but none have demonstrated long-term effectiveness in preventing high myopia and potential complications in adulthood. There is an unmet need for a unified consensus for strategies that balance risk and effectiveness for these methods for personalized myopia management.

Retinal Changes From Hyperopia to Myopia: Not All Diopters Are Created Equal

Purpose

To quantitatively characterize retinal changes across different quantiles of refractive error in 34,414 normal eyes of 23,064 healthy adults in the UK Biobank.

Methods

Twelve optic disc (OD), foveal and vascular parameters were derived from color fundus photographs, correcting for ocular magnification as appropriate. Quantile regression was used to test the independent associations between these parameters and spherical equivalent refraction (SER) across 34 refractive quantiles (high hyperopia to high myopia)-controlling for age, sex and corneal radius.

Results

More negative SER was nonlinearly associated with greater Euclidian (largely horizontal) OD-fovea distance, larger OD, less circular OD, more obliquely orientated OD (superior pole tilted towards the fovea), brighter fovea, lower vascular complexity, less tortuous vessels, more concave (straightened out towards the fovea) papillomacular arterial/venous arcade and wider central retinal arterioles/venules. In myopia, these parameters varied more strongly with SER as myopia increased. For example, while every standard deviation (SD) decrease in vascular complexity was associated with 0.63 D (right eye: 95% confidence interval [CI], 0.58-0.68) to 0.68 D (left eye: 95% CI, 0.63-0.73) higher myopia in the quantile corresponding to -0.60 D, it was associated with 1.61 D (right eye: 95% CI, 1.40-1.82) to 1.70 D (left eye: 95% CI, 1.56-1.84) higher myopia in the most myopic quantile. OD-fovea angle (degree of vertical separation between OD and fovea) was found to vary linearly with SER, but the magnitude was of little practical importance (less than 0.10 D variation per SD change in angle in almost all refractive quantiles) compared with the changes in OD-fovea distance.

Conclusions

Several interrelated retinal changes indicative of an increasing (nonconstant) rate of mechanical stretching are evident at the posterior pole as myopia increases. These changes also suggest that the posterior pole stretches predominantly in the temporal horizontal direction.

Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents

BACKGROUND

Global myopia prevalence poses a substantial public health burden with vision-threatening complications, necessitating effective prevention and control strategies. Precise prediction of spherical equivalent (SE), myopia, and high myopia onset is vital for proactive clinical interventions.

METHODS

We reviewed electronic medical records of pediatric and adolescent patients who underwent cycloplegic refraction measurements at the Eye & Ear, Nose, and Throat Hospital of Fudan University between January 2005 and December 2019. Patients aged 3-18 years who met the inclusion criteria were enrolled in this study. To predict the SE and onset of myopia and high myopia in a specific year, two distinct models, random forest (RF) and the gradient boosted tree algorithm (XGBoost), were trained and validated based on variables such as age at baseline, and SE at various intervals. Outputs included SE, the onset of myopia, and high myopia up to 15 years post-initial examination. Age-stratified analyses and feature importance assessments were conducted to augment the clinical significance of the models.

RESULTS

The study enrolled 88,250 individuals with 408,255 refraction records. The XGBoost-based SE prediction model consistently demonstrated robust and better performance than RF over 15 years, maintaining an R2 exceeding 0.729, and a Mean Absolute Error ranging from 0.078 to 1.802 in the test set. Myopia onset prediction exhibited strong area under the curve (AUC) values between 0.845 and 0.953 over 15 years, and high myopia onset prediction showed robust AUC values (0.807-0.997 over 13 years, with the 14th year at 0.765), emphasizing the models' effectiveness across age groups and temporal dimensions on the test set. Additionally, our classification models exhibited excellent calibration, as evidenced by consistently low brier score values, all falling below 0.25. Moreover, our findings underscore the importance of commencing regular examinations at an early age to predict high myopia.

CONCLUSIONS

The XGBoost predictive models exhibited high accuracy in predicting SE, onset of myopia, and high myopia among children and adolescents aged 3-18 years. Our findings emphasize the importance of early and regular examinations at a young age for predicting high myopia, thereby providing valuable insights for clinical practice.

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.

Initiation of China Alliance of Research in High Myopia (CHARM): protocol for an AI-based multimodal high myopia research biobank

INTRODUCTION

High myopia is a pressing public health concern due to its increasing prevalence, younger trend and the high risk of blindness, particularly in East Asian countries, including China. The China Alliance of Research in High Myopia (CHARM) is a newly established consortium that includes more than 100 hospitals and institutions participating across the nation, aiming to promote collaboration and data sharing in the field of high myopia screening, classification, diagnosis and therapeutic development.

METHODS AND ANALYSIS

The CHARM project is an ongoing study, and its initiation is distinguished by its unprecedented scale, encompassing plans to involve over 100 000 Chinese patients. This initiative stands out not only for its extensive scope but also for its innovative application of artificial intelligence (AI) to assist in diagnosis and treatment decisions. The CHARM project has been carried out using a 'three-step' strategy. The first step involves the collection of basic information, refraction, axial length and fundus photographs from participants with high myopia. In the second step, we will collect multimodal imaging data to expand the scope of clinical information, for example, optical coherence tomography and ultra-widefield fundus images. In the final step, genetic testing will be conducted by incorporating patient family histories and blood samples. The majority of data collected by CHARM is in the form of images that will be used to detect and predict the progression of high myopia through the identification and quantification of biomarkers such as fundus tessellation, optic nerve head and vascular parameters.

ETHICS AND DISSEMINATION

The study has received approval from the Ethics Committee of Beijing Tongren Hospital (TREC2022-KY045). The establishment of CHARM represents an opportunity to create a collaborative platform for myopia experts and facilitate the dissemination of research findings to the global community through peer-reviewed publications and conference presentations. These insights can inform clinical decision-making and contribute to the development of new treatment modalities that may benefit patients worldwide.

TRIAL REGISTRATION NUMBER

ChiCTR2300071219.

Associations between meeting 24-hour movement guidelines and myopia among school-aged children: A cross-sectional study

BACKGROUND

The Canadian 24-hour movement behavior (24-HMB) guidelines recommend an adequate level of physical activity (PA), a limited amount of screen time (ST), and a sufficient sleep duration (SLP) to promote the healthy development of children. Although the positive effects of adhering to the 24-HMB guidelines have been established for several health parameters, less is known about how adherence to the 24-HMB guidelines relates to the myopia risk (i.e., inability to see distant objects properly). Thus, this study investigated associations between meeting 24-HMB guidelines and myopia risk in school-aged children.

METHOD

Using a questionnaire survey, this cross-sectional study was conducted among parents of school-aged children (5-13 years) in China from 15th September to 15th October 2022, with a total of 1423 respondents with complete data for analysis. Parents reported their child's time spent in moderate-to-vigorous-intensity physical activity (MVPA), SLP, and ST. Multiple logistic regression analyses were performed to examine the associations between measures of PA, ST, and SLP alone and in combination, and the occurrence of myopia.

RESULTS

A relatively low percentage of the children being included in the current study (4.92%) met all 24-HMB guidelines, while 32.46% had myopia. Girls had a significantly higher risk of myopia compared to boys (OR = 1.3, 1.002 to 1.68, p = 0.049). Children of parents without myopia had a lower risk of myopia (OR = 0.45, 0.34-0.59, p < 0.001). Children who lived in urban areas (OR = 1.83, 95% CI 1.33 to 2.52, p < 0.001) or towns (OR = 1.60, 1.03 to 2.47, p = 0.04) had a significantly higher risk of myopia compared to those living in rural areas. Meeting SLP guidelines (OR = 0.50, 95% CI 0.31 to 0.82, p < 0.01), meeting ST + SLP guidelines (OR = 0.47, 95% CI 0.32-0.69, <0.001), and meeting all three guidelines were associated with significantly lower risk of myopia (OR = 0.40, 95% CI 0.20-0.82, p = 0.01). Meeting more 24-HMB guidelines was associated with a reduced risk of myopia.

CONCLUSIONS

Our data suggest that adhering to SLP, ST + SLP, and ST + SLP + PA guidelines is associated with the risk of myopia. Future research investigating dose-response associations, and potential mechanisms, is necessary to achieve a more nuanced understanding of the observed associations.

Longitudinal Changes in Axial Length and Spherical Equivalent in Children and Adolescents With High Myopia

Purpose

To investigate longitudinal changes in axial length (AL) and spherical equivalent (SE) in children and adolescents with high myopia and to explore associated risk factors.

Methods

This was a longitudinal, observational cohort study of highly myopic participants (aged 7-17 years) to evaluate the mean rates of change in AL and SE. Mixed effects regression models were used to explore the risk factors.

Results

The sample consisted of 293 participants (mean age at the baseline, 13.63 ± 2.66 years; mean AL, 27.03 ± 1.30 mm diopters; mean SE, -8.99 ± 2.30 diopters) who were followed for 7.09 ± 1.64 years. Pathological myopia (PM) was present in 11.95% of the participants at the baseline. Over the follow-up period, the mean AL and SE progression rates were 0.13 mm/y (95% CI, 0.12-0.14) and -0.36 diopters/y (95% CI, -0.39 to -0.34). The multivariate analysis showed that the AL elongation and myopic SE progression decreased significantly after age 11 (β = -0.080, P < 0.001; β = 0.146, P < 0.001), increased with a greater baseline SE (β = -0.006, P = 0.014; β = 0.017, P = 0.005), and accelerated in children and adolescents who had PM at the baseline (β = 0.043, P = 0.011; β = -0.097, P = 0.025).

Conclusions

A significant association was found between acceleration of AL elongation and myopic SE progression among the children and adolescents with age, especially those younger than 11 years, and the presence of PM.

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.

Advances in artificial intelligence models and algorithms in the field of optometry

The rapid development of computer science over the past few decades has led to unprecedented progress in the field of artificial intelligence (AI). Its wide application in ophthalmology, especially image processing and data analysis, is particularly extensive and its performance excellent. In recent years, AI has been increasingly applied in optometry with remarkable results. This review is a summary of the application progress of different AI models and algorithms used in optometry (for problems such as myopia, strabismus, amblyopia, keratoconus, and intraocular lens) and includes a discussion of the limitations and challenges associated with its application in this field.