Related Experiment Video
Updated: Jan 18, 2026
07:06
Binocular Dynamic Visual Acuity in Eyeglass-Corrected Myopic Patients
Published on: March 29, 2022
3.2K
Early-warning predictive model of retinal detachment in high myopia: a comprehensive construction and validation
Bowen Wang1, Dan Zhao1, Rui Li1
1Department of Ophthalmology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, 430022, China.
BMC Ophthalmology
|January 16, 2026
Summary
This study developed an early warning model for myopic retinal detachment (MRD) using clinical data and fundus imaging. The model accurately identifies high-risk individuals, aiding in timely intervention for preventing vision loss.
Area of Science:
- Ophthalmology
- Medical Imaging
- Predictive Modeling
Background:
- High myopia poses a significant risk for retinal detachment.
- Accurate early detection of myopic retinal detachment (MRD) is crucial for preventing vision impairment.
Purpose of the Study:
- To develop and validate an early warning prediction model for myopic retinal detachment (MRD).
- Integrate clinical indicators, ocular structural parameters, and fundus imaging features for enhanced MRD risk screening.
- Provide a quantitative basis for intervention in high-risk populations.
Main Methods:
- Retrospective analysis of 352 high myopic patients.
- Data included clinical, demographic, ocular biometric, and fundus imaging parameters.
- Random forest, SVM, and logistic regression models were developed and compared using ROC curve analysis.
Main Results:
- Axial length, central macular thickness, vitreous liquefaction, retinal degeneration area, and retinal breaks were identified as independent risk factors for MRD.
- The random forest model demonstrated the highest predictive accuracy with an AUC of 0.890.
- No significant baseline differences were observed between training and validation sets.
Conclusions:
- A robust MRD early warning prediction model was successfully developed and validated.
- Key risk factors for MRD include axial length, central macular thickness, vitreous liquefaction, retinal degeneration, and retinal breaks.
- The model offers clinical utility for risk stratification and guiding follow-up strategies in high-risk myopic patients.
