A MACHINE LEARNING APPROACH FOR PREDICTION OF COVID DEATH RATE USING DESIGN THINKING

Abstract

At the end of 2019, coronavirus (COVID-19) has immediately shown a high rate of transmission, forcing the World Health Organization (WHO) to declare in March 2020 that this unknown coronavirus, named severe acute respiratory syndrome coronavirus 2 (SARS CoV-2), can be characterized as a pandemic. The COVID-19 pandemic has led to a dramatic loss of human life worldwide and presents an unprecedented challenge to public health, food systems and the world of work. The metabolic activity of immune cells is enhanced after a viral infection, such as the one driven by COVID-19. Dietary approaches that support a healthy gut microbiome can benefit the immune system and ensure a good nutritional status that would help the host deal with pathogens. For most, no income means no food, or, at best, less food and less nutritious food. Many researches are being done based on several habits like food, age etc., To predict the COVID - 19 death rate based on dietary habits of 170 countries using machine learning techniques that group the countries together according to the distribution of fat, energy and protein across 23 different types of food as well as amount of kilograms ingested. Results show how obesity and the high consumption of fats appear in countries with the highest death rates, whereas countries with a lower rate have a higher level of cereal consumption accompanied by a lower total average intake of kilocalories. A transformation of the data has been carried out using Principal Component Analysis (PCA). Once the data is reduced, K-Means has been applied with the intention of grouping 170 countries into clusters based on the food consumption. The project is to apply the machine learning concept to analyse the possibility of survival based on the country they live in and if the person is affected by any other diseases. To predict the possibility of the person's survival based on the country he survives using the higher death rate and normal death rate of country clusters and other diseases affected clusters. Based on the cluster using KNN the possibility of survival of the particular person is predicted.