Predicting Clinical Outcomes in Tuberculosis Patients Using Multilayer Perceptron Neural Networks: Interactive Data Analysis and Visualizations

• Ronilson W. S. Pereira State University of Rio de Janeiro (UERJ) http://orcid.org/0000-0002-3851-1338
• Marcos Seruffo Federal University of Pará (UFPA) https://orcid.org/0000-0002-8106-0560
• Karla Figueiredo State University of Rio de Janeiro (UERJ) https://orcid.org/0000-0001-8420-3937

DOI: https://doi.org/10.5753/wide.2024.245491

Abstract

Tuberculosis is one of the world’s leading infectious diseases, and its treatment requires effective data analysis. This study uses Multilayer Perceptron (MLP) Neural Networks and Interactive Visualizations to predict clinical outcomes in tuberculosis patients. The aim is to improve understanding and clinical decision-making through predictive analysis and interactive visualizations. Normalization and balancing techniques were applied to train the MLP model. Interactive tools were used to display data distributions, performance metrics and confusion matrices. The results show that the combination of MLP with interactive visualizations is effective for interpreting clinical outcomes and assisting in treatment planning.

Keywords: Tuberculosis, MLP, Interactive Visualizations

References

Chishtie, J., Bielska, I. A., Barrera, A., Marchand, J.-S., Imran, M., Tirmizi, S. F. A., Turcotte, L. A., Munce, S., Shepherd, J., Senthinathan, A., et al. (2022). Interactive visualization applications in population health and health services research: systematic scoping review. Journal of medical Internet research, 24(2):e27534.

de Almeida Rodrigues, M. G., Sampaio, V., Lynn, T., and Endo, P. T. A brazilian classified data set for prognosis of tuberculosis, between january 2001 and april 2020.

health Organisation, W. (2023). Report 20-23, volume t/malaria/.

Jannah, A. W. and Al Kindhi, B. (2024). Optimization of early detection of tuberculosis: Use of multilayer perceptron and extreme learning machine with clinical data. Jurnal Indonesia Sosial Teknologi, 5(5).

Kanesamoorthy, K. and Dissanayake, M. B. (2021). Prediction of treatment failure of tuberculosis using support vector machine with genetic algorithm. The International Journal of Mycobacteriology, 10(3):279–284.

Maadi, M., Akbarzadeh Khorshidi, H., and Aickelin, U. (2021). A review on human–ai interaction in machine learning and insights for medical applications. International journal of environmental research and public health, 18(4):2121.

Motta, I., Boeree, M., Chesov, D., Dheda, K., Günther, G., Horsburgh Jr, C. R., Kherabi, Y., Lange, C., Lienhardt, C., McIlleron, H. M., et al. (2023). Recent advances in the treatment of tuberculosis. Clinical Microbiology and Infection.

Obeagu, E. and Obeagu, G. (2024). Understanding immune cell trafficking in tuberculosis-hiv coinfection: The role of l-selectin pathways. Elite Journal of Immunology, 2(2):43–59.

Orjuela-Cañón, A. D., Jutinico, A. L., Awad, C., Vergara, E., and Palencia, A. (2022). Machine learning in the loop for tuberculosis diagnosis support. Frontiers in Public Health, 10:876949.

Simarmata, T. S., Isnanto, R. R., and Triwiyatno, A. (2023). Detection of pulmonary tuberculosis using neural network with feature extraction of gray level run-length matrix method on lung x-ray images. In 2023 International Seminar on Intelligent Technology and Its Applications (ISITIA), pages 570–574. IEEE.

Talukder, M. A., Sharmin, S., Uddin, M. A., Islam, M. M., and Aryal, S. (2024). Mlstl-wsn: machine learning-based intrusion detection using smotetomek in wsns. International Journal of Information Security, 23(3):2139–2158.

Viboonsang, P. and Kosolsombat, S. (2024). Network intrusion detection system using machine learning and deep learning. In 2024 IEEE International Conference on Cybernetics and Innovations (ICCI), pages 1–6. IEEE.