Related Experiment Video
Updated: Jun 25, 2025
In vivo Structural Assessments of Ocular Disease in Rodent Models using Optical Coherence Tomography
Published on: July 24, 2020
Ocular Biometric Components in Hyperopic Children and a Machine Learning-Based Model to Predict Axial Length
Jingyun Wang1, Reed M Jost2, Eileen E Birch2,3
1State University of New York College of Optometry, New York, NY, USA.
Insights
Optical biometric components in children with hyperopia change with age, with axial length growth offset by reduced corneal power. A machine learning model accurately predicts axial length using refractive error, age, and sex.
Area of Science:
- Ophthalmology
- Biomedical Engineering
- Pediatric Optometry
Background:
- Hyperopia is common in children and can impact visual development.
- Understanding the changes in ocular biometric parameters with age is crucial for managing pediatric hyperopia.
- Existing methods for axial length estimation may not be optimal for this population.
Purpose of the Study:
- To investigate the development of optical biometric components in children with hyperopia.
- To apply a machine-learning model for predicting axial length in this cohort.
- To provide updated reference data for ocular biometry in pediatric hyperopia.
Main Methods:
- Recruited children aged 3-11 years with hyperopia (+1 D to +10 D).
- Measured axial length, anterior chamber depth, lens thickness, central corneal thickness, and corneal power.
- Utilized classification and regression tree (CART) analysis to predict axial length using spherical equivalent (SEQ), age, and sex.
Main Results:
- Ocular biometric parameters, including axial length and corneal power, showed significant age-related differences.
- Axial length growth was observed to be offset by reductions in corneal power with increasing age.
- The CART model predicted axial length with a lower mean absolute error (0.60 D) compared to linear regression (0.76 D).
Conclusions:
- Ocular biometric parameters evolve with age in hyperopic children, despite similar refractive errors.
- Axial length increases are compensated by decreases in corneal power.
- A machine-learning approach offers a more accurate method for estimating axial length in pediatric hyperopia.
Purpose:
The purpose of this study was to investigate the development of optical biometric components in children with hyperopia, and apply a machine-learning model to predict axial length.
Methods:
Children with hyperopia (+1 diopters [D] to +10 D) in 3 age groups: 3 to 5 years (n = 74), 6 to 8 years (n = 102), and 9 to 11 years (n = 36) were included. Axial length, anterior chamber depth, lens thickness, central corneal thickness, and corneal power were measured; all participants had cycloplegic refraction within 6 months. Spherical equivalent (SEQ) was calculated. A mixed-effects model was used to compare sex and age groups and adjust for interocular correlation. A classification and regression tree (CART) analysis was used to predict axial length and compared with the linear regression.
Results:
Mean SEQ for all 3 age groups were similar but the 9 to 11 year old group had 0.49 D less hyperopia than the 3 to 5 year old group (P < 0.001). With the exception of corneal thickness, all other ocular components had a significant sex difference (P < 0.05). The 3 to 5 year group had significantly shorter axial length and anterior chamber depth and higher corneal power than older groups (P < 0.001). Using SEQ, age, and sex, axial length can be predicted with a CART model, resulting in lower mean absolute error of 0.60 than the linear regression model (0.76).
Conclusions:
Despite similar values of refractive errors, ocular biometric parameters changed with age in hyperopic children, whereby axial length growth is offset by reductions in corneal power.
Translational Relevance:
We provide references for optical components in children with hyperopia, and a machine-learning model for convenient axial length estimation based on SEQ, age, and sex.
