Related Experiment Video
Updated: Jan 17, 2026
Mouse Eye Enucleation for Remote High-throughput Phenotyping
Published on: November 19, 2011
Establishment of a Stacking Machine Learning Model Predicting Cardiac Phenotype in Ectopia Lentis Patients Based on
Linghao Song1,2,3, Ao Miao1,2,3, Xinyue Wang1,2,3
1Eye Institute and Department of Ophthalmology, Eye & ENT Hospital, Fudan University, Shanghai, 200031, China.
Insights
A new machine learning model accurately predicts cardiac issues in ectopia lentis (EL) patients using genetic and eye data. This aids in early diagnosis of related conditions like Marfan syndrome.
Area of Science:
- Ophthalmology
- Cardiology
- Genetics
- Machine Learning
Background:
- Ectopia lentis (EL) is often associated with systemic conditions, including cardiac abnormalities.
- Accurate prediction of cardiac phenotypes in EL patients is crucial for timely intervention.
- Current diagnostic methods may not fully integrate genetic and ocular findings.
Purpose of the Study:
- To develop and validate a stacking machine learning model for predicting cardiac phenotypes in EL patients.
- To utilize both genotypic and phenotypic data for enhanced diagnostic accuracy.
- To explore the potential of this model in facilitating the diagnosis of Marfan syndrome.
Main Methods:
- 151 congenital EL patients were enrolled and categorized based on echocardiography results.
- Genetic screening, ophthalmic, and cardiac follow-ups were conducted.
- A machine learning model was trained using statistically significant parameters (axial length, central corneal thickness, corneal radius of curvature, mutation domain) and validated.
Main Results:
- Significant intergroup differences in axial length and central corneal thickness were observed.
- Specific genotypes (cysteine-eliminating dominant negative, homozygous deficiency mutations) were linked to cardiac predispositions.
- The validated model achieved 75% accuracy in predicting cardiac phenotypes.
Conclusions:
- A reliable machine learning model for cardiac phenotype prediction in EL patients was successfully established.
- The model effectively integrates genotype and ocular phenotype data.
- This approach shows promise for improving the diagnosis of EL-associated conditions, potentially including Marfan syndrome.
Abstract:
Purpose: To establish a stacking machine learning model for cardiac phenotype prediction in ectopia lentis (EL) patients on the basis of their genotype and ocular phenotype. Methods: We enrolled 151 patients with congenital EL and divided them into three groups according to their echocardiograph (normal group, reflux group, and organic lesion group). All the subjects underwent genetic screening and an up-to-1-year ophthalmic and cardiac follow-up. Patients were randomly divided into training set and validation set in a 3:1 ratio. Six statistically significant parameters based on one-way ANOVA and regression analysis were fed into nine basic algorithms for diagnostic training. Results: Among the three groups, intergroup differences in axial length and central corneal thickness were identified. In genotypes, patients with cysteine-eliminating dominant negative and homozygous deficiency mutations were predisposed to cardiac abnormalities. In addition, the corneal radius of curvature and the mutation domain were also included in the experimental dataset. In the validation set, the diagnostic model achieved a comprehensive accuracy of 75% for predicting cardiac phenotype. Conclusion: We established a reliable machine-learning model which predicts cardiac phenotype using genotype and ocular phenotype in EL patients. This model possibly facilitates effective diagnosis of Marfan syndrome.
