Machine Learning model predicts infection with treatment-resistant tuberculosis

Tuberculosis (TB) remains one of the top 10 causes of death worldwide with more than 1.3 million reported deaths in 2020. The emergence and spread of drug-resistant forms of the disease have complicated the fight against tuberculosis in many situations. Adding to the challenge is the fact that treatment of drug-resistant TB is difficult (the success rate was 57% in 2019), long-term (treatment can take 9-20 months) and versatile (treatment often requires multiple antibiotics that have serious side effects). ).

A critical class of antibiotics for the treatment of drug-resistant TB are fluoroquinolones, which form the backbone of most drug-resistant TB therapies. However, TB strains have evolved to become resistant to fluoroquinolones, undermining the efficacy of treatment regimens containing that class of antibiotics. The best treatment options for patients with drug-resistant TB are ideally determined through drug susceptibility testing, which can phenotypically determine the efficacy of antibiotics against a particular TB strain. However, these tests are scarce in resource-poor, high-burden environments, meaning individuals in these regions cannot receive specialized treatment that best manages their TB. In addition, even if they are available, it can take up to 12 weeks for the phenotypic tests to yield results.

Reza Yaesoubi, assistant professor of health policy at the Yale School of Public Health, and his team of researchers have been working on models to predict resistance to fluoroquinolones, which could speed up the process of delivering optimal care. Working with national TB data collected in the Republic of Moldova, the team assessed whether demographic and clinical factors could be used as predictors of TB resistance to fluoroquinolones. They found that information such as age, geographic location and whether the TB disease was new or relapsed were reliable predictors of resistance. They then made a model from this using machine learning to estimate the chance that the patient was infected with a TB strain that is resistant to fluoroquinolone.

“One of the main advantages of these predictive models is that they can be deployed at the point of care, allowing clinicians to optimize the treatment regimen while waiting for the result of drug susceptibility testing, which can take up to 12 weeks,” Yaesoubi said. †

In contrast to the current strategy for the treatment of drug-resistant tuberculosis, which initially assumes susceptibility to fluoroquinolones, Yaesoubi’s model explains how individuals’ conditions influence the likelihood of resistance to fluoroquinolones and when alternative antibiotics (such as delamanid) should be used instead. used.

Through rigorous analysis and testing, the researchers found that the new model had a statistically higher net benefit in pinpointing the right treatment for patients with drug-resistant tuberculosis. These findings promise a system that will enable better treatment of TB patients, Yaesoubi said. Looking ahead, he hopes to extend the model beyond the data collected from the Republic of Moldova to other regions with low resources and high burdens.

“We plan to explore whether similar predictive models can be developed for other critical classes of antibiotics and for other countries with a high burden of drug-resistant tuberculosis,” he said.

The study appears in PLOS Digital Health

Reference: You S, Chitwood MH, Gunasekera KS, et al. Predicting fluoroquinolones resistance in patients with rifampicin-resistant tuberculosis using machine learning methods. PLOS Digital Health† 2022;1(6):e0000059. bye: 10.1371/journal.pdig.0000059

This article has been republished from the following: materials† Note: Material may have been edited for length and content. For more information, please contact the said source.

Leave a Comment

Your email address will not be published.