At the Union World Conference on Lung Health in Copenhagen (18–21 November) researchers presented four main AI approaches that could change how tuberculosis is detected and monitored. TB remained the world’s most deadly infectious disease, causing around 1.25 million deaths in 2024, and many vulnerable communities lack easy access to standard diagnostics.
First, teams from Southern University of Science and Technology and Shenzhen Third People’s Hospital used "breathomics" and machine learning to follow treatment response. They collected breath samples with an AveloMask from around 60 TB patients in South Africa. Liang Fu said the non‑invasive test with machine learning can track recovery early, and could allow safer treatment shortening, better adherence and lower costs.
Second, the Swaasa cough platform, developed with AIIMS, JIPMER and Salcit Technologies, analysed coughs from more than 350 participants. The algorithm identified conditions correctly in 94% of cases and predicted respiratory disease risk in 87% of cases. A mapping tool combined over 20 open datasets with anonymised Ni‑kshay data and reached 71% accuracy for finding the top 20% of villages likely to have undetected TB. Qure.ai’s qXR is the first AI chest X‑ray tool cleared in Europe for children from birth to 15 years. Experts warned that rigorous testing, good datasets and staff training are needed, and that wider validation is still required before scale implementation.
Difficult words
- revolutionize — To completely change something in a good way.
- efficient — Working well without wasting time or resources.
- analyze — To examine something closely to understand it.
- diagnosis — Identifying a disease or condition based on signs.
- non-invasive — Not requiring surgery or special procedures.
- emphasize — To stress or highlight the importance of something.
- reliable — Consistently trustworthy or dependable.reliability
Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.
Discussion questions
- How do you think technology can improve healthcare in the future?
- What are the potential risks of using AI in medical diagnosis?
- In what ways could these advancements benefit underserved communities?
Related articles
Social media can give early warning of displacement
Researchers find that analysing social media posts can give early warning of population movements and help humanitarian agencies respond faster. The study in EPJ Data Science tested methods across three case studies using nearly 2 million posts on X.
Father’s microplastic exposure affects offspring health
A mouse study found that when fathers were exposed to microplastics, their offspring developed metabolic problems. Female offspring showed diabetic signs and researchers linked the effect to changes in sperm small RNAs; the work was published in the Journal of the Endocrine Society.