Glaucoma is a major cause of irreversible blindness worldwide. As glaucoma often presents without symptoms, early detection and intervention are important in delaying progression. Deep learning (DL) has emerged as a rapidly advancing tool to help achieve these objectives. In this narrative review, data types and visualization approaches for presenting model predictions, including models based on tabular data, functional data, and/or structural data, are summarized, and the importance of data source diversity for improving the utility and generalizability of DL models is explored. Examples of innovative approaches to understanding predictions of artificial intelligence (AI) models and alignment with clinicians are provided. In addition, methods to enhance the interpretability of clinical features from tabular data used to train AI models are investigated. Examples of published DL models that include interfaces to facilitate end-user engagement and minimize cognitive and time burdens are highlighted. The stages of integrating AI models into existing clinical workflows are reviewed, and challenges are discussed. Reviewing these approaches may help inform the generation of user-friendly interfaces that are successfully integrated into clinical information systems. This review details key principles regarding visualization approaches in DL models of glaucoma. The articles reviewed here focused on usability, explainability, and promotion of clinician trust to encourage wider adoption for clinical use. These studies demonstrate important progress in addressing visualization and explainability issues required for successful real-world implementation of DL models in glaucoma.

Kim HG, et al. J Korean Med Sci. 2024 Nov;40:e20. https://doi.org/10.3346/jkms.2025.40.e20

The goal of this study is to evaluate the Eye Home Clinic app (ver 1.0), which uses deep learning models to assess the quality of self-captured anterior segment images and detect anterior segment diseases using only the patient’s smartphone. Images undergo quality assessment based on the ‘DL-Image Eligibility’ model, and usable images are analyzed by the ‘DL-Diagnosis’ model to detect one of several anterior segment diseases. A dataset of 1006 images was used for training, and a dataset of 520 images was used for validation. The ‘DL-Image Eligibility’ model achieved an AUC of 0.87, with an accuracy of 0.75. The ‘DL-Diagnosis’ model had higher specificity (0.97) but lower sensitivity (0.29), with an AUC of 0.62. While the app shows potential for anterior segment telemedicine, improvements are needed in the DL model’s sensitivity for detecting abnormalities. Oversampling techniques, transfer learning, and dataset expansion should be considered to enhance the performance in future research. Based on data from users in over 100 countries, significant differences in photo quality among user groups were also identified. iOS users, younger users (21–40 years), and users reporting eye symptoms submitted more usable images. This study underscores the importance of user education and technological advancements to optimize smartphone-based ocular diagnostics.

Objective This study aimed to use deep learning (DL) to develop a cost-effective and accessible screening tool to improve the detection of cognitive decline, a precursor of Alzheimer’s disease (AD). This study integrating a comprehensive battery of neuropsychological tests adjusted for individual demographic variables such as age, sex, and education level.Methods A total of 2,863 subjects with subjective cognitive complaints who underwent a comprehensive neuropsychological assessment were included. A random forest classifier was used to discern the most predictive test combinations to distinguish between dementia and nondementia cases. The model was trained and validated on this dataset, focusing on feature importance to determine the cognitive tests that were most indicative of decline.Results Subjects had a mean age of 72.68 years and an average education level of 7.62 years. The DL model achieved an accuracy of 82.42% and an area under the curve of 0.816, effectively classifying dementia. Feature importance analysis identified significant tests across cognitive domains: attention was gauged by the Trail Making Test Part B, language by the Boston Naming Test, memory by the Rey Complex Figure Test delayed recall, visuospatial skills by the Rey Complex Figure Test copy score, and frontal function by the Stroop Test Word reading time.Conclusion This study showed the potential of DL to improve AD diagnostics, suggesting that a wide range of cognitive assessments could yield a more accurate diagnosis than traditional methods. This research establishes a foundation for future broader studies, which could substantiate the approach and further refine the screening tool.

Gu B, et al. J Korean Glaucoma Soc. 2024 Jun;13(1):24-35. https://doi.org/10.36299/jkgs.2024.13.1.24