MACHINE LEARNING MODELS FOR DRY EYES DIAGNOSIS

To develop reliable Machine Learning (ML) models capable of using demographic and real-world clinical data to predict dry eye severity and dry eye type and dry eye treatment in surgical and non-surgical models.

 

Currently, 25118 assessments have been performed in over 253 clinics. There are 495 doctors using the system. A total of 21190 questionaires have been compiled.

Real-world clinical data captured over span of 18 months were used to develop two machine learning diagnostic models for severity and type of dry eye. Correlation feature selection (CFS) was used to eliminate redundant and irrelevant features. Using stratified 10-fold cross-validation was shown to be the most effective ML technique. Support Vector Machines (SVM) was the best technique to fit our data. We developed two SVM models, namely SM (dry eye severity model) and TM (dry eye type model). The two models used the exact feature for prediction.

 

The SM model was successful in predicting different dry eye severity cases at AUC−ROC of 0.79 and AUC−PR of 0.61. Furthermore, the TM model was successful in predicting different dry eye type cases at AUC−ROC of 0.91 and AUC−PR of 0.94.

Machine Learning models proposed in this study accurately predicted dry eye severity and type. Such models may improve health outcomes and provide early alerting to potentially prevent the progression of dry eye disease. We are looking at predicted diagnosis and treatment directed towards the diagnosis to improve non-surgical and surgical outcomes. Finally, more future data incorporation will further enhance these models.