Year: 2024
Type: article
Abstract: In individuals with diabetes, the occurrence of heart failure varies from 9% to 22%, marking a fourfold rise compared to the general population. This heightened prevalence is particularly pronounced in diabetic patients aged 60 years or older. Recent studies highlight a rapid increase in mortalities related to cardiomyopathies, attributed to the alarming surge in cases of type 2 diabetes mellitus. Global epidemics like diabetes and heart failure (HF) often referred to as the “deadly duo,” pose a significant burden on society due to heightened hospitalization costs and a grim prognosis. Therefore, it is necessary to implement new strategies for improving the diagnosis and treatment of diabetes and heart failure. Early diagnosis of diabetes and heart failure may have results in keeping patients healthy and it helps in reducing the risk factors of such serious complications. Currently, the application of artificial intelligence (AI) and Machine Learning (ML) in the field of diabetes has increased which may help improve the classification system and may have the possibility to solve this problem at an early stage. In this article, our aim is to examine the multifaceted relationship between diabetes and heart failure using (AI/ML). The application of AI and ML in diabetes and heart failure research has been widely explored in basic biomedical research. Therefore, in this review, we highlighted the impactful use of AI/ML in underlying mechanisms of diabetic cardiomyopathy by using various therapeutic drugs to explore the risk factors and consider their implications on patient response. By unraveling this intricate relationship, we can strive to enhance our knowledge to pave the way for improved preventive measures, early detection, and more effective management of these intertwined titans.
Authors: Kaiser Jamil, Shivakumar Yerra, Javed Ahmed Tantray, M. Asimuddim
Institution: Mahavir Medical Research Centre
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4408202625