Classification of Vital Genetic Syndromes Associated With Diabetes Using ANN-Based CapsNet Approach

Classification of Vital Genetic Syndromes Associated With Diabetes Using ANN-Based CapsNet Approach

Rajesh N., Amalraj Irudayasamy, M. Syed Khaja Mohideen, C. Prasanna Ranjith
Copyright: © 2022 |Pages: 18
DOI: 10.4018/IJeC.307133
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Diabetes has been linked to a wide range of genetic abnormalities or disorders like Cushing syndrome, Wolfram’s syndrome. The factual significance of these relatively uncommon disorders originates from the knowledge that supplies into the potential processes driving prevalent diabetes. Diabetes-related syndromes are presently classified based on clinical and biochemical characteristics. However, until now, no expertise classification strategies are developed for classifying diabetes-associated syndrome disorders efficiently and accurately. Thus, we introduce an Artificial Neural Network framework based on CapsNets to categorize vital genetic disorders related to diabetes. Here, a capsule represents a bundle or set of neurons used to retain data about an essential subject and provides precise information in each image. The suggested approach was systematically compared using cutting-edge methods and basic classification models. With an overall 91.4 percent accuracy, the proposed CapsNets-based method provides the best sensitivity89.93%, specificity 90.77%, and F1-score value 93.10%
Article Preview
Top

1. Introduction

Diabetes mellitus is a severe chronic condition that affects millions of people worldwide. Elevated blood glucose levels characterize diabetes due to inadequate insulin production or sometimes compromised metabolic actions or both (Lonnappan et al., 2007). The long-term complications of diabetes may include cardiovascular dysfunction, renal damages, stroke, cardiac arrest, and other heart-related problems, as well as issues with the blood arteries and nerves in the legs and feet (Krasteva et al., 2011 and Nathan., DM., 1993). Diabetes afflicted approximately 122,000,000 inhabitants globally in 1980, and this number rose to almost 422,000,000 by 2014 (NCD-RisC, 2017). About 642,000,000 people will live with diabetes in the world by 2040. Furthermore, diabetes was directly responsible for almost 1.6 million fatalities worldwide (Bharath et al., 2017). As a result, it's a concerning number for everyone. Daily increases in diabetes cases are resulting in daily increases in diabetic fatalities. Type I and type II diabetic (T1D and T2D) and Gestational diabetes mellitus (GDM) are the three categories of diabetes (Danaei et al., 2011). T1D is most often seen in younger people under the age of 30.

Diabetes Mellitus (DM) is becoming more prevalent in human beings' everyday lives as living conditions improve. As a result, the question of how could rapidly and correctly diagnose and evaluate diabetes deserves more investigation. Usually, there seem to be three methods to diagnose diabetes in the medical community: glucose tolerance test (GTT), a fasting glycemic level, and a blood sugar level that occurs at random (ADA, 2012, Cox and Edelman., 2009, Iancu et al., 2008).

While diabetes mellitus is more common in people with several genetic disorders, four frequent associated syndromes were studied and classified using the Deep advanced learning (DL) model. Thus, this article concerns Cushing syndrome, Wolfram's syndrome, Huntington's chorea, and Friedreich's ataxia. Figure 1, Figure 2, Figure 3, and Figure 4 depicts sample images of Cushing syndrome, Wolfram's syndrome, Huntington's chorea, and Friedreich's ataxia respectively.

Cushing Syndrome: It's possible to develop Cushing's syndrome (CS) if the blood has excessive amounts of the anxiety hormone known to be cortisol. Uncontrolled cortisol levels raise the pressure level and more glucose concentrations in the blood, and ultimately, severe diabetic complications may arise as a consequence. DM often accompanies Cushing syndrome as a side effect. In individuals receiving long-term glucocorticoid treatment, DM is more common than previously thought. A frequent side effect of long-term use of corticosteroids leads to severe hyperglycemia, and diabetes has indeed been associated with a greater likelihood of mortality and morbidity for people with CS.

Figure 1.

Clinical image feature of CS

IJeC.307133.f01

Wolfram Syndrome: Wolfram Syndrome (WS) is always examined as “autosomal recessive disorder”, also known to be “DIDMOAD” (Diabetes insipidus-Diabetes Mellitus-Optic Atrophy-Deafness), causes diabetes especially in youth, chronic neurological deterioration, and endocrine malfunction. However, there are still a lot of researchers who don't comprehend Wolfram syndrome and its exact associativeness with diabetes. Symptoms of WS include hyperglycemia owing to insulin deficiency (DM) and gradual vision loss caused by neuron degeneration that passes from the eyes to the significant nervous sectors of the brain, which is often referred to as “optic atrophy”.

Figure 2.

Clinical Image Features of WS

IJeC.307133.f02

Complete Article List

Search this Journal:
Reset
Volume 20: 1 Issue (2024)
Volume 19: 7 Issues (2023)
Volume 18: 6 Issues (2022): 3 Released, 3 Forthcoming
Volume 17: 4 Issues (2021)
Volume 16: 4 Issues (2020)
Volume 15: 4 Issues (2019)
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing