Beyond isolated cough events: AI-based tuberculosis screening through temporal analysis of cough sounds
Discuss this preprint
Start a discussion What are Sciety discussions?Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Tuberculosis (TB) is a major global health challenge, with many cases remaining undiagnosed due to limited access to screening and diagnostic services. Artificial intelligence (AI) systems based on cough sound analysis offer a scalable and accessible approach to TB screening, but most previous studies have analysed isolated cough events, despite the possibility that diagnostically useful information is encoded in the temporal dynamics of cough episodes. We evaluated an AI-based screening framework using cough recordings collected under real-world clinical conditions from 500 participants in Zambia, including 201 individuals with bacteriologically confirmed TB, 150 symptomatic patients with other respiratory diseases, and 149 healthy controls.
Using multiple pre-trained speech foundation models fine-tuned on cough sounds, we systematically investigated the influence of temporal context by varying the audio input window from 1 to 6 s, measured from the onset of each cough episode. Across all evaluated models, diagnostic performance consistently peaked with a 3 s input window, indicating that useful information extends beyond individual cough events and is encoded within the short-term temporal dynamics of cough episodes. The best audio-only model achieved an area under the receiver operating characteristic curve (AUROC) of 85.2% for distinguishing TB from all other participants and 80.1% for distinguishing TB from symptomatic non-TB respiratory disease. Incorporating demographic and clinical variables improved AUROC to 92.1% and 84.2%, respectively.
Performance remained robust across recording devices, participants with HIV co-infection, and varying acoustic conditions. These findings demonstrate that preserving temporal context improves AI-based cough screening for TB and suggest that analysing cough episodes, rather than isolated cough events, may enhance diagnostic performance in real-world settings. More broadly, the results highlight the importance of temporal context in the design of future respiratory sound datasets and AI-based diagnostic systems.
Author summary
Tuberculosis remains one of the world’s leading infectious diseases, and early detection is essential for reducing transmission and improving treatment outcomes. Cough is a common symptom of pulmonary tuberculosis and can be recorded using widely available devices such as smartphones, making cough sound analysis a potentially accessible screening approach. Most previous studies have analysed isolated cough sounds, but we investigated whether information contained in the temporal evolution of cough episodes could improve screening performance. Our study included people with bacteriologically confirmed tuberculosis, symptomatic patients with other respiratory diseases, and healthy individuals. Using AI models trained on cough sounds, we examined how much temporal context was needed for accurate screening. We found that analysing audio input window of approximately three seconds consistently outperformed shorter audio input, suggesting that diagnostically useful information is encoded not only within individual cough sounds but also in their short-term temporal dynamics. The system achieved strong performance in distinguishing tuberculosis from non-tuberculosis participants and remained robust across different recording devices and background acoustic conditions. These findings demonstrate the potential of AI-driven cough sound analysis as a practical and scalable screening tool for tuberculosis, particularly in resource-constrained settings, and highlight the importance of preserving temporal context when developing future respiratory sound datasets and diagnostic algorithms.
