Tuberculosis (TB), a communicable disease caused by Mycobacterium tuberculosis, is a major cause of ill health and one of the leading causes of death worldwide. Until the COVID-19 pandemic, TB was the leading cause of death from a single infectious agent, ranking even above HIV/AIDS.
In 2020, an estimated 9.9 million people fell ill with TB and 1.3 million died of TB worldwide. However, approximately 40% of people with TB were not diagnosed or reported to public health authorities because of challenges in accessing health facilities or failure to be tested or treated when they do. The development of low-cost, non-invasive digital screening tools may improve some of the gaps in diagnosis.
As coughing is a common symptom of TB, it has the potential to be used as a biomarker for diagnosis of disease. Several previous studies have demonstrated the potential for cough sounds to be used to screen for TB, though these were typically done in small samples or limited settings. Further development and evaluation are critical to move the field forward.
Here we leverage data collected from people who presented to clinics across 7 countries with new or worsening cough for at least 2 weeks. Elicited coughs were recorded using the Hyfe Research app. They were then comprehensively evaluated for TB with sputum-based molecular (Xpert MTB/RIF Ultra) and culture (MGIT or Lowenstein-Jensen) testing.
The CODA TB DREAM Challenge will ask participants to predict TB status using features extracted from elicited coughs, either in the presence or absence of demographic and clinical factors used routinely for TB screening.
