Smartphone Technology Screens for Tuberculosis by Cough Sounds

February 2024

Salma Ismail

Scientists at the University of Washington and Kenya's Center for Respiratory Diseases Research are leveraging cutting-edge technology to develop a novel screening tool that harnesses the power of smartphone apps.

The urgency for such a tool is underscored by the resurgence of TB cases globally, necessitating cost-effective and accessible diagnostic methods, particularly in regions with limited healthcare resources. While traditional TB tests like sputum culture or GeneXpert molecular tests are highly accurate, their affordability remains a concern in the most affected areas.

The tool is trained to recognize subtle nuances in cough characteristics, including those imperceptible to the human ear, that distinguish TB-related coughs from those caused by other respiratory conditions. By minimizing background noise and environmental variability, TBscreen demonstrates promising accuracy in distinguishing TB coughs, achieving an overall accuracy rate of approximately 82%.

The study involved recording coughs from both TB patients and individuals with other respiratory conditions. Through meticulous analysis of over 33,000 passive coughs and 1,200 forced coughs, TBscreen showcased its ability to discern TB-related coughs with impressive accuracy.

This isn't the first instance of leveraging cough sounds for TB diagnosis. Last year, researchers at the University of California, San Francisco, developed a similar cell phone app for monitoring cough frequency among TB patients across various regions heavily impacted by the disease.

With TB remaining a significant global health concern, innovations like TBscreen offer hope in the fight against this infectious disease. By harnessing the widespread availability of smartphones, this technology holds the potential to revolutionize TB screening, paving the way for earlier detection and improved patient outcomes.

TBscreen represents leveraging digital health solutions to tackle one of humanity's oldest infectious diseases. With further development and implementation, this innovative approach may not only transform TB diagnosis but also advance research in detecting other pulmonary conditions, offering a beacon of progress in global healthcare.

References

---

Manuja Sharma et al, TBscreen: A passive cough classifier for tuberculosis screening with a controlled dataset, Science Advances (2024). DOI: 10.1126/sciadv.adi0282