Making cough count in tuberculosis care

Abstract

Cough assessment is central to the clinical management of respiratory diseases, including tuberculosis (TB), but strategies to objectively and unobtrusively measure cough are lacking. Acoustic epidemiology is an emerging field that uses technology to detect cough sounds and analyze cough patterns to improve health outcomes among people with respiratory conditions linked to cough. This field is increasingly exploring the potential of artificial intelligence (AI) for more advanced applications, such as analyzing cough sounds as a biomarker for disease screening. While much of the data are preliminary, objective cough assessment could potentially transform disease control programs, including TB, and support individual patient management. Here, we present an overview of recent advances in this field and describe how cough assessment, if validated, could support public health programs at various stages of the TB care cascade.

Keywords: Diagnostic markers; Prognostic markers; Tuberculosis.

Fig. 1. Digital cough spectrograms for artificial intelligence algorithm analysis.

a Waveform image of a pulmonary TB cough. b Spectrogram conversion of the waveform cough. On the spectrogram, acoustic information is represented as frequency (y-axis) and amplitude (color) over time (x-axis).

Fig. 2. Potential use cases for digital cough monitoring in the tuberculosis cascade of care.

Each step in the TB care cascade is represented as a bar. The gaps in the cascade are in red between each step. Boxes pointing at the gaps represent possible digital cough-based solutions to address various gaps. The height of the bar graphs and the length of the gaps are not scaled to represent true values. They are intended to help illustrate the different steps of the care cascade and points at which people with TB may fail to benefit from care. (Cascade of care adapted from Fig. 1 of Subbaraman et al.).

Fig. 3. Example use of smartphone-based cough screening application for community-based monitoring.

In this vignette, a female is experiencing symptoms of disease, including cough. Using a phone with the example Health App (not a real app), she is prompted to cough and report any other symptoms she is experiencing. The AI algorithm in the Heath App uses the information to provide likely causes of disease (in this case, COVID-19 or TB) and refers her to consult a physician for confirmatory testing. (Vignette originally created for The Lancet Citizens’ Commission on Reimagining India’s Health System, by Raghu Dharmaraju, Vijay Chandru, Umakant Soni, and Shubraneel Ghosh, ARTPARK (AI & Robotics Technology Park) at Indian Institute of Science. “A vignette from 2030 in rural India: How might technology enable citizen-centered health journeys?” https://www.artpark.in/reimagine-health/2030_rural_india).