In a recent Devex thought leadership piece, EPCON's CEO Caroline Van Cauwelaert highlights a stark reality: TB has once again become the world’s leading infectious killer, surpassing COVID-19. Despite decades of global efforts to eliminate TB, progress has been slow. The pandemic further disrupted control measures, exacerbating the crisis. However, AI-powered solutions are emerging as a game-changer in the fight against TB, offering new hope in diagnostics, patient identification, and disease management.
Today, over 10 million people develop TB annually, with 1.25 million deaths in 2023 alone – unbelievably, nearly double the deaths due to HIV / AIDS. The burden is heaviest on vulnerable populations with limited access to timely diagnosis and treatment. In Africa, for example, the continent accounts for 23% of global TB cases and 33% of deaths. Without urgent intervention, the gap will only widen.
The promise of AI in TB diagnosis and managementThe WHO has frequently stated that “finding people with TB” is a primary bottleneck in confronting this disease. AI is changing the game by enabling faster, more accurate, and scalable solutions, including:
Predictive analytics for early detection: AI models can analyse large-scale clinical, epidemiological and environmental datasets to identify high-risk individuals. We’ve concluded that an AI-driven approach can be 75% more accurate in identifying high risk areas compared to conventional methods.
AI-powered diagnostics: By enhancing image analysis and improving rapid test protocols, AI enables TB screening with higher accuracy – even in remote areas where trained radiologists are scarce. Early detection saves lives.
Optimised treatment strategies: AI facilitates personalised treatment plans and better resource allocation. For example, in South Africa, public health organisation Aquity Innovations used AI to improve resource distribution – leading to the discovery of 1,300 patients with the help of just 20 community health care workers.
A call to action
To unlock AI’s potential in the fight against TB and other communicable diseases, we need an approach that includes:
Strategic partnerships: Collaboration between technology providers, healthcare organisations, and government agencies is essential.
Investment in infrastructure: AI solutions are dependent on the digital and data infrastructure, including data collection, supporting them.
Policy and regulation: Governments must create enabling environments for AI adoption in healthcare, including policies for data sharing, privacy protection, and integration with existing health systems.
Capacity building: Healthcare workers and local teams need training and support to implement and interpret AI-driven insights.
On the upside, AI solutions can be used to address a variety of health challenges, from COVID-19 immunisation to preventing mother-to-child HIV transmission. Success stories abound. In Nigeria, for example, AI-driven TB detection programs helped identify 12,000 additional TB cases that would otherwise have been missed. In Nelson Mandela Bay, South Africa, AI-enhanced screening boosted TB detection rates from 0.2% to 0.9% – a significant improvement in case identification.
Van Cauwelaert concluded her article with a powerful call to action: The question is no longer whether AI can help us combat TB and other infectious diseases—it’s how quickly we can scale these solutions to save more lives.