Cough acoustic analysis using artificial intelligence for COVID-19 detection: A comparative study of patient cohorts from Lima, Peru and Montreal, Canada

Purpose Digital cough screening for COVID-19 detection shows promise, but population differences in cough acoustics and screening accuracy require investigation. This study examined cough characteristics and COVID-19 screening performance in Lima, Peru and Montreal, Canada. Methods Cough recordings and clinical data were prospectively collected from 605 adults. COVID-19 and other respiratory pathogens were diagnosed via NAAT. Acoustic features were extracted and compared. COVID-19 classification used eXtreme Gradient Boosting (XGBoost) and a deep learning neural network, assessed via internal and external validations for audio-only, clinical-only, and combined models. A sub-analysis explored XGBoost prediction scores by underlying disease status. Results Significant heterogeneity in cough acoustic features existed between Lima and Montreal cohorts. XGBoost audio-based models trained and tested in Lima showed superior performance (area under the curve [AUC]: 0.71 ± 0.08) compared to Montreal (AUC: 0.53 ± 0.04). Both models demonstrated poor external validation performance when tested on the alternate dataset. Neural network models showed similar trends. Additionally, individuals with other respiratory diseases had differing COVID-19 prediction scores between sites, suggesting epidemiological context influences model performance. Conclusions Cough acoustics are population-specific, impacting cough-based classification algorithm utility across different epidemiological settings. COVID-19 cough screening models demonstrated limited transferability, highlighting challenges in developing globally applicable tools without representative training data.