skip to main content


Title: Simulations of Diabetic and Non-Diabetic Peripheral Nerve Myelin Lipid Bilayers
Award ID(s):
2003912
NSF-PAR ID:
10281203
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
The Journal of Physical Chemistry B
Volume:
125
Issue:
23
ISSN:
1520-6106
Page Range / eLocation ID:
6201 to 6213
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    The most common eye infection in people with diabetes is diabetic retinopathy (DR). It might cause blurred vision or even total blindness. Therefore, it is essential to promote early detection to prevent or alleviate the impact of DR. However, due to the possibility that symptoms may not be noticeable in the early stages of DR, it is difficult for doctors to identify them. Therefore, numerous predictive models based on machine learning (ML) and deep learning (DL) have been developed to determine all stages of DR. However, existing DR classification models cannot classify every DR stage or use a computationally heavy approach. Common metrics such as accuracy, F1 score, precision, recall, and AUC-ROC score are not reliable for assessing DR grading. This is because they do not account for two key factors: the severity of the discrepancy between the assigned and predicted grades and the ordered nature of the DR grading scale. 

    This research proposes computationally efficient ensemble methods for the classification of DR. These methods leverage pre-trained model weights, reducing training time and resource requirements. In addition, data augmentation techniques are used to address data limitations, improve features, and improve generalization. This combination offers a promising approach for accurate and robust DR grading. In particular, we take advantage of transfer learning using models trained on DR data and employ CLAHE for image enhancement and Gaussian blur for noise reduction. We propose a three-layer classifier that incorporates dropout and ReLU activation. This design aims to minimize overfitting while effectively extracting features and assigning DR grades. We prioritize the Quadratic Weighted Kappa (QWK) metric due to its sensitivity to label discrepancies, which is crucial for an accurate diagnosis of DR. This combined approach achieves state-of-the-art QWK scores (0.901, 0.967 and 0.944) in the Eyepacs, Aptos, and Messidor datasets.

     
    more » « less
  2. null (Ed.)
    Abstract Skeletal muscle is a tissue that is directly involved in the progression and persistence of type 2 diabetes (T2D), a disease that is becoming increasingly common. Gaining better insight into the mechanisms that are affecting skeletal muscle dysfunction in the context of T2D has the potential to lead to novel treatments for a large number of patients. Through its ability to emulate skeletal muscle architecture while also incorporating aspects of disease, tissue-engineered skeletal muscle (TE-SkM) has the potential to provide a means for rapid high-throughput discovery of therapies to treat skeletal muscle dysfunction, to include that which occurs with T2D. Muscle precursor cells isolated from lean or obese male Zucker diabetic fatty rats were used to generate TE-SkM constructs. Some constructs were treated with adipogenic induction media to accentuate the presence of adipocytes that is a characteristic feature of T2D skeletal muscle. The maturity (compaction and creatine kinase activity), mechanical integrity (Young's modulus), organization (myotube orientation), and metabolic capacity (insulin-stimulated glucose uptake) were all reduced by diabetes. Treating constructs with adipogenic induction media increased the quantity of lipid within the diabetic TE-SkM constructs, and caused changes in construct compaction, cell orientation, and insulin-stimulated glucose uptake in both lean and diabetic samples. Collectively, the findings herein suggest that the recapitulation of structural and metabolic aspects of T2D can be accomplished by engineering skeletal muscle in vitro. Impact Statement The tissue engineering of skeletal muscle to model disease and injury has great promise to provide a tool to develop and/or improve therapeutic approaches for improved health care. A tissue-engineered skeletal muscle model of one of the most common and debilitating diseases, type 2 diabetes, has been developed in vitro as evidenced by the structural and metabolic alterations that are consistent with the disease phenotype in vivo. 
    more » « less
  3. Abstract Diabetic nephropathy, a kidney complication arising from diabetes, is the leading cause of death in diabetic patients. Unabated, the growing epidemic of diabetes is increasing instances of diabetic nephropathy. Although the main causes of diabetic nephropathy have been determined, the mechanisms of their combined effects on cellular and tissue function are not fully established. One of many damages of diabetic nephropathy is the development of fibrosis within the kidneys, termed mesangial expansion. Mesangial expansion is an important structural lesion that is characterized by the aberrant proliferation of mesangial cells and excess production of matrix proteins. Mesangial expansion is involved in the progression of kidney failure in diabetic nephropathy, yet its causes and mechanism of impact on kidney function are not well defined. Here, we review the literature on the causes of mesangial expansion and its impacts on cell and tissue function. We highlight the gaps that still remain and the potential areas where bioengineering studies can bring insight to mesangial expansion in diabetic nephropathy. 
    more » « less