Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Oct 14:10:e2246.
doi: 10.7717/peerj-cs.2246. eCollection 2024.

Model for predicting drug resistance based on the clinical profile of tuberculosis patients using machine learning techniques

Igor Wenner Silva Falcao  1 , Diego Lisboa Cardoso  1 , Albert Einstein Coutinho Dos Santos Santos  1 , Erminio Paixao  1 , Fernando Augusto R Costa  2 , Karla Figueiredo  3 , Saul Carneiro  4 , Marcos César da Rocha Seruffo  1
Affiliations

Model for predicting drug resistance based on the clinical profile of tuberculosis patients using machine learning techniques

Igor Wenner Silva Falcao et al. PeerJ Comput Sci. .

Abstract

Tuberculosis (TB) is a disease caused by the bacterium Mycobacterium tuberculosis and despite effective treatments, still affects millions of people worldwide. The advent of new treatments has not eliminated the significant challenge of TB drug resistance. Repeated and inadequate exposure to drugs has led to the development of strains of the bacteria that are resistant to conventional treatments, making the eradication of the disease even more complex. In this context, it is essential to seek more effective approaches to fighting TB. This article proposes a model for predicting drug resistance based on the clinical profile of TB patients, using machine learning techniques. The model aims to optimize the work of health professionals directly involved with tuberculosis patients, driving the creation of new containment strategies and preventive measures, as it specifies the clinical data that has the greatest impact and identifies the individuals with the greatest predisposition to develop resistance to anti-tuberculosis drugs. The results obtained show, in one of the scenarios, a probability of development of 70% and an accuracy of 84.65% for predicting drug resistance.

Keywords: Anti-tuberculosis; Drug resistance; Machine learning; Tuberculosis.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Figure 1
Figure 1. The figure illustrates the workflow of the prediction model according to the proposed architecture, which has four execution steps (Preprocessing, Clustering, Segmentation, and Learning).
Execution is limited to the training flow, represented by a solid line. The figure was created using the Draw.io tool from Google (https://www.drawio.com/doc/faq/usage-terms). All icons used in the figure are free icons available in Draw.io and can be used under the Creative Commons license (CC BY 4.0).
Figure 2
Figure 2. Three distinct clusters regarding opportunistic comorbidities and drug resistance in tuberculosis patients.
In Cluster A, smoking and alcoholism are associated with high resistance to antituberculosis drugs. In Cluster B, only alcoholism stands out as a risk factor. In Cluster 3, HIV and drug addiction show a strong association with drug resistance, increasing the risk for patients with HIV/TB coinfection. These results underscore the importance of considering multiple factors in tuberculosis treatment. The figure was created using the Python programming language with the Plotly library (https://plotly.com/python/). All icons used in the figure are free icons available under the Creative Commons license (CC BY 4.0).
Figure 3
Figure 3. The results of probability distribution using logistic regression.
The larger the “candle”, the greater the probability dispersion within each cluster. The Figure was created using the Python programming language with the Plotly library (https://plotly.com/python/). All icons used in the figure are free icons available under the Creative Commons license (CC BY 4.0).
See this image and copyright information in PMC

References

    1. Amiri MRJ, Siami R, Khaledi A. Tuberculosis status and coinfection of pulmonary fungal infections in patients referred to reference laboratory of health centers ghaemshahr city during 2007–2017. Ethiopian Journal of Health Sciences. 2018;28(6):683–690. doi: 10.4314/ejhs.v28i6.2. - DOI - PMC - PubMed
    1. Ashna H, Kaffash A, Khaledi A, Ghazvini Mutations of rpob gene associated with rifampin resistance among mycobacterium tuberculosis isolated in tuberculosis regional reference laboratory in northeast of Iran during 2015–2016. Ethiopian Journal of Health Sciences. 2018;28(3):299–304. doi: 10.4314/ejhs.v28i3.7. - DOI - PMC - PubMed
    1. Biagioni BT, Cavicchioli M, Massabni AC. Silver complexes for tuberculosis treatment: a short review. Química Nova. 2022;45:83–88. doi: 10.21577/0100-4042.20170812. - DOI
    1. BRASIL A. Bactérias de tuberculose resistentes a antibióticos desafiam. 2018. https://agenciabrasil.ebc.com.br/geral/noticia/2018-01/ https://agenciabrasil.ebc.com.br/geral/noticia/2018-01/ (accessed 31 January 2024)
    1. Cao F, Liang J, Li D, Bai L, Dang C. A dissimilarity measure for the k-modes clustering algorithm. Knowledge-Based Systems. 2012;26(5):120–127. doi: 10.1016/j.knosys.2011.07.011. - DOI

LinkOut - more resources