Analysis and Prediction of Cholera Disease using Machine Learning Algorithms

Abstract

In this research, we have investigated Cholera disease and its fatality rate from previous years in terms of various countries. This disease is not new, yet researchers are currently utilising several approaches to detect the difficulties and extract hidden information from previous records. This study proposed an alternative solution in terms of Cholera disease. Several traditional machine learning algorithms are experimented with to analyse and predict the disorder from the existing dataset. The proposed research methodology has consisted of four phases, for instance, Research Dataset, Data Preprocessing and Algorithm Selection. Our investigation shows that the Gradient Boosting algorithm performs well in this type of dataset with an accuracy of 93%. We have discovered the R2 score, Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE) are 0.932841%, 398.1827%, 158549.4724%, and 71.6621098%, respectively. We have carried out an exploratory data analysis where Cholera case data analysis of Bangladesh has been done from 1996 to 2000. In addition to the disease prediction, data analysis of different countries has been carried out, and correlations have been made through which the interrelationships of each indicator can be found very quickly.