Postsurgery Classification of Best-Corrected Visual Acuity Changes Based on Pterygium Characteristics Using the...

Area of Science:

• Ophthalmology
• Computer Science
• Medical Imaging

Background:

• Pterygium progression can lead to visual impairment.
• Accurate prediction of visual outcomes is essential for patient management.
• Morphological characteristics of pterygium influence visual acuity.

Purpose of the Study:

• To develop a machine learning model for predicting best-corrected visual acuity (BCVA) changes after pterygium surgery.
• To evaluate the effectiveness of different machine learning algorithms in classifying post-surgery BCVA outcomes.
• To correlate pterygium morphological features with post-surgery visual acuity predictions.

Main Methods:

• Retrospective analysis of 93 pterygium patient datasets.
• Utilized RapidMiner software with four machine learning algorithms.
• Evaluated model performance based on accuracy, specificity, and sensitivity.

Main Results:

• The Support Vector Machine (SVM) model demonstrated the highest performance.
• SVM achieved an average accuracy of 94.44% (±5.86%).
• SVM showed 100% specificity and 92.14% (±8.33%) sensitivity.

Conclusions:

• Machine learning algorithms can accurately classify post-surgery BCVA changes in pterygium patients.
• Pterygium characteristics are valuable predictors for post-surgery visual outcomes.
• The SVM model shows significant potential for clinical application in pterygium management.