Prediction of myopia development among Chinese school-aged children using refraction data from electronic medical records: A retrospective, multicentre machine learning study

Abstract

Background

Electronic medical records provide large-scale real-world clinical data for use in developing clinical decision systems. However, sophisticated methodology and analytical skills are required to handle the large-scale datasets necessary for the optimisation of prediction accuracy. Myopia is a common cause of vision loss. Current approaches to control myopia progression are effective but have significant side effects. Therefore, identifying those at greatest risk who should undergo targeted therapy is of great clinical importance. The objective of this study was to apply big data and machine learning technology to develop an algorithm that can predict the onset of high myopia, at specific future time points, among Chinese school-aged children.

Methods and findings

Real-world clinical refraction data were derived from electronic medical record systems in 8 ophthalmic centres from January 1, 2005, to December 30, 2015. The variables of age, spherical equivalent (SE), and annual progression rate were used to develop an algorithm to predict SE and onset of high myopia (SE ≤ −6.0 dioptres) up to 10 years in the future. Random forest machine learning was used for algorithm training and validation. Electronic medical records from the Zhongshan Ophthalmic Centre (a major tertiary ophthalmic centre in China) were used as the training set. Ten-fold cross-validation and out-of-bag (OOB) methods were applied for internal validation. The remaining 7 independent datasets were used for external validation. Two population-based datasets, which had no participant overlap with the ophthalmic-centre-based datasets, were used for multi-resource validation testing. The main outcomes and measures were the area under the curve (AUC) values for predicting the onset of high myopia over 10 years and the presence of high myopia at 18 years of age. In total, 687,063 multiple visit records (≥3 records) of 129,242 individuals in the ophthalmic-centre-based electronic medical record databases and 17,113 follow-up records of 3,215 participants in population-based cohorts were included in the analysis. Our algorithm accurately predicted the presence of high myopia in internal validation (the AUC ranged from 0.903 to 0.986 for 3 years, 0.875 to 0.901 for 5 years, and 0.852 to 0.888 for 8 years), external validation (the AUC ranged from 0.874 to 0.976 for 3 years, 0.847 to 0.921 for 5 years, and 0.802 to 0.886 for 8 years), and multi-resource testing (the AUC ranged from 0.752 to 0.869 for 4 years). With respect to the prediction of high myopia development by 18 years of age, as a surrogate of high myopia in adulthood, the algorithm provided clinically acceptable accuracy over 3 years (the AUC ranged from 0.940 to 0.985), 5 years (the AUC ranged from 0.856 to 0.901), and even 8 years (the AUC ranged from 0.801 to 0.837). Meanwhile, our algorithm achieved clinically acceptable prediction of the actual refraction values at future time points, which is supported by the regressive performance and calibration curves. Although the algorithm achieved balanced and robust performance, concerns about the compromised quality of real-world clinical data and over-fitting issues should be cautiously considered.

Conclusions

To our knowledge, this study, for the first time, used large-scale data collected from electronic health records to demonstrate the contribution of big data and machine learning approaches to improved prediction of myopia prognosis in Chinese school-aged children. This work provides evidence for transforming clinical practice, health policy-making, and precise individualised interventions regarding the practical control of school-aged myopia.

Abstract

Therapies to control myopia progression confer significant side effects and should be targeted to those at highest risk. Here, Yizhi Liu and colleagues report a machine learning algorithm that predicts the progression of myopia, into early adulthood, among Chinese school-aged children.

Author summary

Why was this study done?

• Myopia has reached epidemic levels among young adults in East and Southeast Asia, affecting an estimated 80%–90% of high school graduates, with approximately 20% of them having high myopia. Various interventions, including atropine eyedrops and orthokeratology, have been proposed to control myopia progression; however, these approaches confer significant side effects. Identifying those at greatest risk who should undergo targeted therapy is the most important clinical challenge faced by ophthalmologists and optometrists.

• Electronic medical records provide large-scale real-world clinical data for use in developing clinical decision systems. Taking school-aged myopia, the most prevalent eye disease, as an example, it would be of great value to use ophthalmic-centre-based electronic medical records to develop a big-data-driven clinical prediction algorithm based on machine learning algorithms.

What did the researchers do and find?

• This study analysed 687,063 longitudinal electronic medical records from the largest ophthalmic centres in China and developed and validated individualised prediction models for myopia prediction based on machine learning techniques.

• Our model predicted spherical equivalent and onset of high myopia at 18 years of age at a clinically acceptable accuracy and as early as 8 years in advance.

What do these findings mean?

• The algorithm, which was trained and validated using a large real-world dataset, was able to predict the presence of high myopia with clinically acceptable accuracy among Chinese school-aged populations.

• Large-scale, long-term electronic medical records and machine learning algorithms provide unique opportunities for the development of prediction models for progressive diseases, such as myopia in school-aged children.

• Our findings have great potential to change current approaches used to manage school myopia by paediatric and general ophthalmologists as well as general practitioners and optometrists, who are often the first point of care.