Technological advancement has a profound effect on all spheres of life, whether in the medical field or in any other field. Artificial intelligence has shown promising results in health care by making its decisions by analyzing and processing data. To prevent the spread and development of a life-threatening disease, the most important step is its early diagnosis. COVID-19 is a highly contagious disease, and has become a global epidemic that needs to be addressed as soon as possible. Due to its rapid speed of spreading comes the need for a system which can be used to detect the virus. With the increase in use of technology, lots of data about COVID-19 is readily available at our fingertips, which can be used to obtain important information about the virus. In this project, we compared the accuracies of different machine learning algorithms in predicting COVID-19 and used the most accurate one in the final model testing.
In December 2019, the novel coronavirus appeared in the city of Wuhan in China [1] and was reported to the World Health Organization (WHO) on 31 December 2019. The virus posed a global threat and was named COVID-19 by the WHO on the 11th. February 2020. W.H.O declared the outbreak a public health emergency [2] and stated the following; “the virus is spread through the respiratory tract when a healthy person comes in contact with an infected person”. An infected person shows symptoms within 2-14 days. According to W.H.O the symptoms and signs of moderate to severe conditions are dry cough, fatigue and fever while in severe cases dyspnea, fever and fatigue may occur. People with other illnesses such as asthma, diabetes, and heart disease are at greater risk of contracting the virus and may become seriously ill. A system which can be used to detect the virus has become necessary due to the rapid spread of the virus, killing hundreds of thousands of people. Machine learning classification algorithms, data sets and machine learning software are essential tools for designing the COVID-19 predictive model. This project aims to compare different machine learning algorithms like K-nearest neighbors, Random forest and Naive Bayes with respect to their accuracies and then use the best one among them to develop a system which predicts whether a person has COVID or not using the data provided to the model.
[1] Wu F, Zhao S, Yu B, Chen YM, Wang W, Song ZG, Hu Y, Tao ZW, Tian JH, Pei YY, Yuan ML, Zhang YL, Dai FH, Liu Y, Wang QM, Zheng JJ, Xu L, Holmes EC, Zhang YZ (2020) A new coronavirus associated with human respiratory disease in china. Nature 44(59):265–269 https://www.nature.com/articles/s41586-020-2008-3[1]
[2] Medscape Medical News, The WHO declares public health emergency for novel coronavirus (2020) https://www.medscape.com/viewarticle/924596[2]
[3] A. F. M. Batista, J. L. Miraglia, T. H. R. Donato and A. D. P. C. Filho, ”COVID-19 diagnosis prediction in emergency care patients: a machine learning approach”, medRxiv, 2020 https://www.medrxiv.org/content/10.1101/2020.04.04.20052092v2.full. pdf[3]
[4] M. R. H. Mondal, S. Bharati, P. Podder and P. Podder, ”Data analytics for novel coronavirus disease”, Informatics in Medicine Unlocked Elsevier, vol. 20, pp. 100374, 2020 https://www.researchgate.net/publication/342195015 Data analytics for novel coronavirus disease[4]
[5] D. Goodman-Meza, A. Rudas, J. N. Chiang, P. C. Adamson, J. Ebinger et al., ”A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity”, PLOS ONE, vol. 15, no. 9, pp. e0239474, 2020. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7508387/[5]
[6] P. Schwab, A. D. Sch¨utte, B. Dietz and S. Bauer, ”Clinical predictive models for COVID-19: systematic study”, J Med Internet Res, vol. 22, no. 10, pp. e21439, 2020.https://www.jmir.org/2020/10/e21439/[6]
[7] Y. Sun, V. Koh, K. Marimuthu, O. T. Ng, B. Young, S. Vasoo, M. Chan et al., ”Epidemiological and clinical predictors of COVID-19”, Clin Infect Dis, vol. 71, no. 15, pp. 786-792, Jul 2020. https://academic.oup.com/cid/article/71/15/786/5811426[7]
[8] Z. Meng, M. Wang, H. Song, S. Guo, Y. Zhou, W. Li et al., ”Development and utilization of an intelligent application for aiding COVID-19 diagnosis”, medRxiv, 2020. https://www.medrxiv.org/content/10.1101/2020.03.18.20035816v1[8]