Related Experiment Video
Updated: Dec 31, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
A practical model for the identification of congenital cataracts using machine learning
Duoru Lin1, Jingjing Chen1, Zhuoling Lin1
1State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Jinsui Road #7, Guangzhou, Guangdong 510060, People's Republic of China.
Insights
This study developed accurate models to identify infants at high risk for congenital cataracts (CCs), a leading cause of childhood blindness. These models can aid in early detection, especially in underserved regions.
Area of Science:
- Ophthalmology
- Pediatrics
- Public Health
Background:
- Congenital anomalies affect approximately 1 in 33 newborns globally.
- Congenital cataracts (CCs) are the primary cause of preventable childhood blindness.
- Effective identification models for infants at high risk of CCs are needed.
Purpose of the Study:
- To develop a practical and accurate model for identifying infants at high risk of congenital cataracts (CCs).
- To assess the model's performance in diverse clinical settings, including those with low disease prevalence.
Main Methods:
- A case-control study involving 2005 subjects (1274 CC cases, 731 controls).
- Development of CC identification models using random forest and adaptive boosting, based on birth conditions, family history, and environmental factors.
- Validation through internal cross-validation, external validation, and simulated clinical environments with varying CC prevalence.
Main Results:
- The developed CC identification models demonstrated high discrimination accuracy (AUC=0.91-0.96).
- Key risk factors identified include family history of CC, low parental education, and comorbidity.
- Models maintained stable performance across validation tests and simulated clinical scenarios.
Conclusions:
- The CC identification models accurately distinguish CC patients from healthy children.
- These models show potential as a complementary screening tool for congenital cataracts.
- The models are particularly valuable for screening in undeveloped and remote areas with limited healthcare access.
Background:
Approximately 1 in 33 newborns is affected by congenital anomalies worldwide. We aimed to develop a practical model for identifying infants with a high risk of congenital cataracts (CCs), which is the leading cause of avoidable childhood blindness.
Methods:
This case-control study was performed in the Zhongshan Ophthalmic Center and involved 2005 subjects, including 1274 children with CCs and 731 healthy controls. The CC identification models were established based on birth conditions, family medical history, and family environmental factors using the random forest (RF) and adaptive boosting methods (trained by 1129 CC cases and 609 healthy controls), which were tested by internal 4-fold cross-validation and external validation (145 CC cases and 122 healthy controls). The models were also tested using 4 datasets with gradually reduced proportions of CC patients (bilateral cases) to validate their performance in an approximate simulation of a clinical environment with a relatively low disease prevalence.
Findings:
The CC identification models showed high discrimination in both the 4-fold cross validation (area under the curve (AUC)=0.91 [95% confidence interval: 0.88-0.94] in bilateral cases; 0.82 [0.77-0.89] in unilateral cases) and external validation (AUC=0.93±0.05 in bilateral cases; 0.86±0.01 in unilateral cases), and achieved stable performance in the clinical tests (AUC=0.94-0.96 in the four subgroups by RF). Furthermore, family history of CC, low parental education level, and comorbidity were identified as the top three most relevant factors to both bilateral and unilateral CC diagnosis.
Interpretation:
Our CC identification models can accurately discriminate CC patients from healthy children and have the potential to serve as a complementary screening procedure, especially in undeveloped and remote areas.
