Diabetic retinopathy (DR) is a severe microvascular complication of diabetes that affects the eyes, leading to progressive damage to the retina and potential vision loss. Timely intervention and detection are crucial for preventing irreversible damage. With the advancement of technology, deep learning (DL) has emerged as a powerful tool in medical diagnostics, offering a promising solution for the early prediction of DR. This study compares four convolutional neural network architectures, DenseNet201, ResNet50, VGG19, and MobileNetV2, for predicting DR. The evaluation is based on both accuracy and training time data. MobileNetV2 outperforms other models, with a validation accuracy of 78.22%, and ResNet50 has the shortest training time (15.37 s). These findings emphasize the trade-off between model accuracy and computational efficiency, stressing MobileNetV2’s potential applicability for DR prediction due to its balance of high accuracy and a reasonable training time. Performing a 5-fold cross-validation with 100 repetitions, the ensemble of MobileNetV2 and a Graph Convolution Network exhibits a validation accuracy of 82.5%, significantly outperforming MobileNetV2 alone, which shows a 5-fold validation accuracy of 77.4%. This superior performance is further validated by the area under the receiver operating characteristic curve (ROC) metric, demonstrating the enhanced capability of the ensemble method in accurately detecting diabetic retinopathy. This suggests its competence in effectively classifying data and highlights its robustness across multiple validation scenarios. Moreover, the proposed clustering approach can find damaged locations in the retina using the developed Isolate Regions of Interest method, which achieves almost a 90% accuracy. These findings are useful for researchers and healthcare practitioners looking to investigate efficient and effective powerful models for predictive analytics to diagnose diabetic retinopathy.

As life expectancy increases, cognitive impairments such as Alzheimer's disease (AD) create serious problems for older adults. Women regardless of ethnicity and age group, are disproportionately affected, accounting for two-thirds of AD cases, with post-menopausal women representing over 60 % of those affected. Sarcopenia, defined by gradual reduction of skeletal muscle mass, strength, and activities, is increasingly correlated with an elevated risk of cognitive decline in post-menopausal women. Menopause-related hormonal decline (particularly estrogen loss) and aging contribute to sarcopenia, characterized by muscle mitochondrial dysfunction, oxidative stress, and insulin resistance. This sarcopenia-driven reduction in muscle mass and functional capacity further reduces the production of myokines (e.g., BDNF, irisin), impairing neuronal proliferation, adult neurogenesis, and spatial learning/memory. These pathophysiological changes show a contributing link between sarcopenia and AD progression in post-menopausal women. This review is unique in that it discusses the triangular interplay between menopause, sarcopenia, and AD, offering an integrated mechanistic framework that links hormonal decline, muscle loss, and neurodegeneration. We aim to clarify the pathophysiological causes behind the muscle-brain axis and suggest viable treatment approaches to slow down sarcopenia and cognitive deterioration in postmenopausal women based on current evidence. The formulation of targeted strategies for enhancing the quality of life and lessening healthcare expenditures in this expanding population depends on the advancement of understanding this complex interconnection between menopause, sarcopenia and cognition.