A new research project, coordinated by Stellenbosch University, aims to develop and validate a new non-sputum-based diagnostic solution for tuberculosis (TB) that combines AI-powered chest X-ray analysis with a simple fingertip blood test.
The project combines fingertip blood testing with AI technology to improve TB detection in settings with limited healthcare access.
The project, known as AddiCAD, combines computer-aided detection of TB on chest radiographs (CAD4TB), which is an AI system that analyses digital chest X-rays for signs of tuberculosis, with a biomarker test measuring the body's immune response to infection.
By integrating these two data sources, AddiCAD aims 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 to CAD4TB alone, without sacrificing sensitivity.
