Post-stroke respiratory complications using machine learning with voice features from mobile devices

Background: Abnormal voice may identify those at risk of post-stroke aspiration. This study was aimed to determine whether machine learning algorithms with voice recorded via a mobile device can accurately classify those at risk of tube feeding and post-stroke aspiration pneumonia and be used as digital biomarkers. Methods: Voice samples from patients referred for swallowing disturbance in a university-affiliated hospital were collected prospectively using a mobile device. Subjects that required tube feeding were further classified to high risk of respiratory complication, based on the voluntary cough strength and abnormal chest x-ray images. Results: A total of 449 samples were obtained, with 234 requiring tube feeding and 113 showing high risk of respiratory complications. The eXtreme gradient boosting multimodal models that included abnormal acoustic features and clinical variables showed high sensitivity levels of 88.7% (95% CI, 82.6–94.7) and 84.5% (95% CI, 76.9–92.1) in the classification of those at risk of tube feeding and at high risk of respiratory complications; respectively. In both cases, voice features proved to be the strongest contributing factors in these models. Conclusions: Voice features may be considered as a viable digital biomarker in those at risk of respiratory complications related to post-stroke swallowing disturbance.