Diabetic Retinopathy and Diabetic Macular Edema in People With Early-Onset Diabetes

Hybrid Explainable Artificial Intelligence Models for Targeted Metabolomics Analysis of Diabetic Retinopathy

BACKGROUND

Diabetic retinopathy (DR) is a prevalent microvascular complication of diabetes mellitus, and early detection is crucial for effective management. Metabolomics profiling has emerged as a promising approach for identifying potential biomarkers associated with DR progression. This study aimed to develop a hybrid explainable artificial intelligence (XAI) model for targeted metabolomics analysis of patients with DR, utilizing a focused approach to identify specific metabolites exhibiting varying concentrations among individuals without DR (NDR), those with non-proliferative DR (NPDR), and individuals with proliferative DR (PDR) who have type 2 diabetes mellitus (T2DM).

METHODS

A total of 317 T2DM patients, including 143 NDR, 123 NPDR, and 51 PDR cases, were included in the study. Serum samples underwent targeted metabolomics analysis using liquid chromatography and mass spectrometry. Several machine learning models, including Support Vector Machines (SVC), Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), and Multilayer Perceptrons (MLP), were implemented as solo models and in a two-stage ensemble hybrid approach. The models were trained and validated using 10-fold cross-validation. SHapley Additive exPlanations (SHAP) were employed to interpret the contributions of each feature to the model predictions. Statistical analyses were conducted using the Shapiro-Wilk test for normality, the Kruskal-Wallis H test for group differences, and the Mann-Whitney U test with Bonferroni correction for post-hoc comparisons.

RESULTS

The hybrid SVC + MLP model achieved the highest performance, with an accuracy of 89.58%, a precision of 87.18%, an F1-score of 88.20%, and an F-beta score of 87.55%. SHAP analysis revealed that glucose, glycine, and age were consistently important features across all DR classes, while creatinine and various phosphatidylcholines exhibited higher importance in the PDR class, suggesting their potential as biomarkers for severe DR.

CONCLUSION

The hybrid XAI models, particularly the SVC + MLP ensemble, demonstrated superior performance in predicting DR progression compared to solo models. The application of SHAP facilitates the interpretation of feature importance, providing valuable insights into the metabolic and physiological markers associated with different stages of DR. These findings highlight the potential of hybrid XAI models combined with explainable techniques for early detection, targeted interventions, and personalized treatment strategies in DR management.

Preservation of Intrinsically Photosensitive Retinal Ganglion Cells (ipRGCs) in Late Adult Mice: Implications as a Potential Biomarker for Early Onset Ocular Degenerative Diseases

Purpose

Intrinsically photosensitive retinal ganglion cells (ipRGCs) play a crucial role in non-image-forming visual functions. Given their significant loss observed in various ocular degenerative diseases at early stages, this study aimed to assess changes in both the morphology and associated behavioral functions of ipRGCs in mice between 6 (mature) and 12 (late adult) months old. The findings contribute to understanding the preservation of ipRGCs in late adults and their potential as a biomarker for early ocular degenerative diseases.

Methods

Female and male C57BL/6J mice were used to assess the behavioral consequences of aging to mature and old adults, including pupillary light reflex, light aversion, visual acuity, and contrast sensitivity. Immunohistochemistry on retinal wholemounts from these mice was then conducted to evaluate ipRGC dendritic morphology in the ganglion cell layer (GCL) and inner nuclear layer (INL).

Results

Morphological analysis showed that ipRGC dendritic field complexity was remarkably stable through 12 months old of age. Similarly, the pupillary light reflex, visual acuity, and contrast sensitivity were stable in mature and old adults. Although alterations were observed in ipRGC-independent light aversion distinct from the pupillary light reflex, aged wild-type mice continuously showed enhanced light aversion with dilation. No effect of sex was observed in any tests.

Conclusions

The preservation of both ipRGC morphology and function highlights the potential of ipRGC-mediated function as a valuable biomarker for ocular diseases characterized by early ipRGC loss. The consistent stability of ipRGCs in mature and old adult mice suggests that detected changes in ipRGC-mediated functions could serve as early indicators or diagnostic tools for early-onset conditions such as Alzheimer's disease, Parkinson's disease, and diabetes, where ipRGC loss has been documented.