New AI Tools Offer Hope for Global TB Elimination
The battle against tuberculosis (TB) has received a powerful boost with the unveiling of cutting-edge AI tools. From smartphone cough analysis to child-friendly screening systems, these innovations promise to revolutionize TB detection, monitoring, and prevention, especially in underserved communities.
The advancements were showcased at the Union World Conference on Lung Health in Copenhagen, Denmark, from November 18-21. They highlight the potential for faster, more accessible, and personalized TB care, addressing the challenges posed by traditional diagnostics that remain out of reach for many.
Guy Marks, president of the International Union against Tuberculosis and Lung Disease, emphasized the transformative power of AI in the fight against TB and lung disease, stating, 'The challenge now is ensuring these innovations reach the people and health systems that need them most.'
TB remains the world's leading infectious killer, causing approximately 1.25 million deaths in 2024, according to the World Health Organization (WHO). Many vulnerable communities are difficult to reach, underscoring the critical need for accurate and accessible diagnostics.
Breath Test Breakthrough
Scientists from the Southern University of Science and Technology and Shenzhen Third People's Hospital in China presented an AI-powered breath analysis system for tracking TB treatment responses. This system, called 'breathomics,' involves analyzing chemical compounds in exhaled breath using machine learning.
In a study involving around 60 TB patients in South Africa, researchers used the AveloMask to collect breath samples and identified subtle chemical changes in exhaled air with machine learning. The results suggested that a non-invasive breath test combined with machine learning can effectively track recovery during TB treatment and predict early treatment outcomes.
Liang Fu, a pulmonologist and TB specialist, stated, 'Our study indicates that a non-invasive breath test combined with machine learning can track recovery during TB treatment and indicate early when a patient is doing well. This approach could enable safer treatment shortening, improve adherence, and reduce costs for patients and TB programs.'
Cough Analysis and Beyond
Researchers from the All India Institute of Medical Sciences (AIIMS), Jawaharlal Institute of Postgraduate Medical Education and Research, and Salcit Technologies introduced Swaasa, an AI platform that analyzes cough sounds using a smartphone. The AI is trained to distinguish TB-related coughs from those caused by other respiratory illnesses, offering a low-cost diagnostic alternative in resource-limited settings.
The study revealed that the AI algorithm accurately identified underlying conditions in 94% of cases and predicted the risk of respiratory diseases in 87% of cases. Rakesh Kumar, an associate professor at the Centre for Community Medicine at AIIMS, highlighted the system's scalability and potential for large-scale deployment.
Vulnerability Mapping for TB Control
To enhance active TB case-finding in India's National Tuberculosis Elimination Programme, researchers from the Wadhwani Institute for AI presented an AI-driven vulnerability mapping system. This system combines demographic, geographic, and economic data with anonymized case data from India's Ni-kshay TB surveillance system.
The study achieved 71% accuracy in identifying the top 20% of villages most likely to have undetected TB cases during national testing. Aparna Chaudhary, the national TB lead at Wadhwani AI, emphasized the system's potential to increase precision and efficiency in TB case finding and guide resource allocation.
Child TB Screening with AI
Qure.ai, a Mumbai-based health tech company, unveiled qXR, an AI-powered child TB screening tool designed for use from birth to 15 years. It is the first AI-enabled chest X-ray tool to receive European regulatory clearance for this age range, including the youngest children.
Shibu Vijayan, the chief medical officer, global health at Qure.ai, expressed pride in equipping healthcare systems worldwide with a scalable and reliable method for early TB detection, prioritizing care, and ultimately saving lives.
However, Ketho Angami, president of India's Access to Rights and Knowledge (ARK) Foundation, emphasizes the importance of rigorous testing for these new technologies. He warns that while more tools are needed, the key issue is whether AI technologies can provide clear and reliable conclusions.
Angami states, 'If their accuracy, efficacy, and specificity are well validated, then that is a positive development. But without a strong and well-supported dataset, relying on such tools becomes risky.' He also stresses the importance of training AI system managers to interpret results and go beyond the system's outputs.
As AI continues to evolve in the fight against TB, the focus on accessibility, accuracy, and ethical considerations will be crucial in ensuring its successful implementation and impact on global health.
