Machine Learning Models for the Diagnosis of Dry Eyes Using Real-world Clinical Data.

Introduction: Dry eye disease (DED) is a common ocular condition marked by discomfort and tear film instability. Machine learning (ML) techniques are increasingly recognized for their potential to transform healthcare, particularly in ophthalmology. Methods: This study aims to develop ML models for predicting the severity and type of DED using demographic and clinical data. Real-world clinical data collected over 18 months served as the basis for creating two diagnostic models. The data set comprised 1,313 well-structured samples, each annotated by domain experts, showcasing multiple demographic and clinical features. A correlation feature selection technique was used to eliminate redundant and irrelevant features. Through stratified 10-fold cross-validation, two support vector machine models – dry eye severity model (SM) and dry eye type model (TM) – were developed to predict the severity and type of DED. Results: The SM achieved a moderate performance in predicting the severity of dry eye cases, with an area under the receiver operating characteristic (AUC-ROC) of 0.79 and an area under the precision-recall (AUC-PR) of 0.61. Furthermore, the TM demonstrated effectiveness in predicting different dry eye types, yielding an AUC-ROC of 0.91 and an AUC-PR of 0.83. We also verified the robustness of both SM and TM by comparing their performance with nine baseline ML methods. Both SM and TM consistently outperformed the baseline methods in terms of AUC-ROC and AUC-PR. Conclusion: The potential application of these models lies in improving health outcomes and offering early alerts to potentially prevent the progression of DED. [ABSTRACT FROM AUTHOR]