Researchers at Klick Labs have unveiled a cutting-edge, non-invasive technique that can predict chronic high blood pressure (hypertension) with a high degree of accuracy using just a person's voice.
Published in the peer-reviewed journal IEEE Access, the findings may hold potential for advancing the early detection of chronic high blood pressure and showcase a novel way to harness vocal biomarkers for better health outcomes.
The study’s 245 participants were asked to record their voices by speaking into a mobile app developed by the Klick scientists, which detected high blood pressure with accuracies up to 84 percent for females and 77 percent for males.
Hidden sonic clues
The app uses machine learning to analyze hundreds of vocal biomarkers that are indiscernible to the human ear, including pitch variability, patterns of speech energy distribution, and sharpness of sound changes (spectral contrast).
“By leveraging various classifiers and establishing gender-based predictive models, we discovered a more accessible way to detect hypertension, which we hope will lead to earlier intervention for this widespread global health issue," said Klick scientists in a statement.
Klick Labs is collaborating with hospitals, academic institutions, and public health authorities worldwide.
Citation: B. Taghibeyglou, J. M. Kaufman and Y. Fossat, "Machine Learning-Enabled Hypertension Screening Through Acoustical Speech Analysis: Model Development and Validation," in IEEE Access, vol. 12, pp. 123621-123629, 2024. https://ieeexplore.ieee.org/document/10669945 (open-access)
Thumbnail image credit: A. Angelica, DALL E