Article Preview
Top1. Introduction
The applications of artificial intelligence (AI) have been interpreted in a number of ways. Understanding, learning, and reasoning are all skills that are utilised to analyze and solve problems. AI uses a number of technologies to imitate certain aspects of human intelligence. Over the last few decades, Medicine and health care in general have benefited from AI methodologies and tools. The objective of this study is to use AI technologies to make them easier to comprehend for diabetes health care during covid pandemic. AI medical applications include diagnosis, categorization, therapy, and robotics, among others. To date, neural networks and fuzzy logic (FL) are the most widely utilised AI technologies. Other methods and technologies, on the other extreme, were chosen and included in this evaluation due to their significance.
Artificial intelligence (AI) is a rapidly evolving science, and its applications to diabetes, a global epidemic, have the potential to revolutionise the way diabetes is diagnosed and managed. Machine learning principles have been utilised to generate algorithms to support predictive models for the risk of diabetes and its complications. In the management of diabetes, digital therapies have proven to be a reliable intervention for lifestyle therapy. Patients are more empowered to manage their diabetes on their own, and clinical decision support benefits both patients and health care providers. The use of artificial intelligence enables for continuous and painless remote monitoring of a patient's symptoms and biomarkers. In the case of diabetes, technological advancements have aided in resource optimization. AI will usher in a paradigm shift in diabetes care, moving away from traditional management tactics and toward data-driven precision care (Ellahham, 2020).
Corona viruses are a type of single-stranded RNA genome enclosed virion. The Corona virus Disease (COVID-19) initially emerged in December 2019 in Wuhan, China. It was swiftly detected as a rapidly spreading infectious disease, and by March 2020, it had spread around the globe, causing the WHO to declare it a pandemic (Muniyappa and Gubbi, 2020). In this global health calamity, the healthcare system is looking for innovative technologies to direct and manage the spreading of the COVID-19 (Coronavirus) outbreak (Hu-Ge, et al., 2010).
The severe acute respiratory syndrome virus 2 (SARS-CoV-2)-caused Coronavirus Disease 2019 (COVID-19) was initially detected in December 2019 and quickly spread to most cities and countries throughout the world. SARS-CoV-2 is mostly spread through respiratory droplets during face-to-face contact. Mild upper respiratory tract infection symptoms, as well as potentially severe sepsis and shock, may be caused by the infection. In vulnerable populations, such as the elderly with comorbidities, it may cause serious and deadly consequences. SARS-CoV-2 has infected over 200 countries and caused massive losses, with over 120 million confirmed cases and 2.6 million deaths as of March 16, 2021. COVID-19's escalating incidence and large casualties put a strain on already stretched hospital resources. To improve the clinical efficiency of healthcare systems and streamline the diagnosis, treatment, and surveillance of COVID-19, effective technologies are required. Artificial intelligence is a promising technology, according to recent studies, because it can achieve better scale-up, accelerate processing power, and even surpass people in some healthcare activities.
Artificial intelligence (AI) is an area of algorithm-based applications that enable machines to solve knowledge issues and employ algorithms to replicate human decision-making, all while continuously improving performance by applying inputted data to specified tasks. High sensitivity and specificity in detecting the object, speed of reporting, and consistency of outcomes are all advantages of AI. AI has made great progress in recent years, particularly in predictive machine learning models for medical care. Deep learning is a machine learning technique that is based on the intricate topologies of Artificial Neural Networks (ANN). Deep learning demonstrates strong discriminative performance if adequate training data sets are provided, and it is required for prediction. Artificial intelligence and machine learning (AI/ML) technologies in medicine attempt to improve the quality of medical care, boost diagnostic accuracy, reduce potential errors, and forecast outcomes by uncovering new insights from massive amounts of data generated by many patients' experiences.