In what is expected to be an important weapon in the fight against tuberculosis, Stellenbosch University is leading AddiCAD, a R46m international project to improve diagnosis by combining AI-powered chest X-ray analysis with a simple fingerstick blood test – the blend of cutting-edge science and real-world usability expected to make accurate diagnosis more accessible where it is needed most.
The project, to speed up detection in settings with limited healthcare access, is being co-ordinated by the university and funded by the Global Health European and Developing Countries Clinical Trials Partnership 3 (Global Health EDCTP3).
One of the major challenges in the fight against TB is effective detection: of the estimated 10.7m new cases each year, around 2.5m people remain undiagnosed.
This is partly because current diagnostic tools are often too expensive, laboratory-dependent or difficult to deploy at the point of care.
The AddiCAD project was officially launched in May 2026 with €2.5m in funding from Global Health EDCTP3. It brings together six partners from Africa and Europe with complementary expertise in clinical research, diagnostics, artificial intelligence, data science and implementation. These are Delft Imaging Systems (Netherlands), Life SADX (South Africa), LINQ Management GmbH (Germany), the London School of Hygiene & Tropical Medicine (UK and The Gambia), Stellenbosch University, and the University of Namibia.
Combining AI imaging with biomarker science
The novel approach brings together two promising technologies in a single diagnostic model. AddiCAD combines CAD4TB, an AI system that analyses digital chest X-rays for signs of TB, with a biomarker test measuring the body’s immune response to infection.
By integrating these data sources, AddiCAD hoped to provide more accurate results than either method can achieve on its own.
The project builds on preliminary findings showing that AddiCAD achieved a 20% improvement in specificity compared with CAD4TB alone, without sacrificing sensitivity. This means the combined approach could help reduce false-positive results while still identifying people who are likely to have TB – an important step towards more efficient and reliable diagnosis in high-burden settings.
Where rapid diagnosis is needed most
The innovation has the potential to transform TB screening and diagnosis in resource-limited settings. Rather than relying solely on sputum samples, which can be difficult to obtain and process, healthcare workers could use AddiCAD to rapidly identify people most likely to have TB and ensure they receive prompt further testing and treatment.
With the project now under way, the consortium members will develop the novel biosensor and a companion mobile application before validating the solution in a clinical study involving 1 000 adults with presumptive TB across South Africa, Namibia and The Gambia.
The team will also work closely with healthcare providers, patient representatives, regulators and commercial partners to support future implementation and scale-up.
If the initial findings are validated, implementation of AddiCAD may enable life-saving treatment to many additional patients.
AddiCAD is one of two Global Health EDCTP3-funded research projects currently co-ordinated by Stellenbosch University to advance TB diagnostics. Alongside PRECISE-TBM, which focuses on improving the diagnosis of childhood TB meningitis, the three-year project reflects a broader effort to develop faster, more accessible diagnostic solutions for high-burden settings.
See more from MedicalBrief archives:
SA to expedite TB diagnosis/treatment as cases continue to soar
More than half of South Africans do not seek TB treatment – HSRC survey