Screening of Tuberculosis (TB) and Coronavirus (COVID-19) using Machine Learning

DOI

10.2991/978-94-6463-589-8_39How to use a DOI?

Keywords

disease prediction; TB; COVID-19; machine learning

Abstract

Tuberculosis (TB) affects more than 10 million individuals annually, making it a significant global health issue. Due to the emergence of the COVID-19 pandemic, TB services in numerous countries have experienced temporary interruptions, resulting in a possible delay in the detection of TB patients and a significant number of cases going unnoticed. Because of the similarities in symptoms and their impact on the respiratory system, there is a potential for misdiagnosis of both disorders. Misdiagnosis or delayed diagnosis might lead to severe consequences, such as the spread of the diseases and postponed medical intervention. This study attempts to evaluate the performance of three machine learning techniques (Random Forest, Naïve Bayes and XGBoost) to determine whether individuals may be identified as potentially having either TB or COVID-19 based on their symptoms. The study used three measurements: accuracy, mean squared error and root mean squared error. The results indicate the effectiveness of machine learning in differentiating between TB and COVID-19, with XGBoost achieving the highest accuracy of 74.99% compared with Naïve Bayes (65.13%) and Random Forest (70.93%). The study also conducted experiments using feature selection methods to identify the common important symptoms for predicting both TB and COVID-19. The findings indicated that four symptoms are significant. Overall, the effectiveness of diverse machine learning techniques in predicting TB and COVID-19 using electronic health records suggests that machine learning can be effectively employed to determine appropriate therapy and efficient triage.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nurliyana Suhaimi
AU  - Nor Azimah Khalid
AU  - Marshima Mohd Rosli
PY  - 2024
DA  - 2024/12/01
TI  - Screening of Tuberculosis (TB) and Coronavirus (COVID-19) using Machine Learning
BT  - Proceedings of the International Conference on Innovation & Entrepreneurship in Computing, Engineering & Science Education (InvENT 2024)
PB  - Atlantis Press
SP  - 430
EP  - 440
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-589-8_39
DO  - 10.2991/978-94-6463-589-8_39
ID  - Suhaimi2024
ER  -