Researchers at Klick Labs have unveiled an advanced, non-invasive technique that can predict chronic high blood pressure (hypertension) with a high degree of accuracy using just a person’s voice. Just published in the peer-reviewed journal IEEE Accessthe findings offer tremendous potential for advancing the early detection of chronic high blood pressure and demonstrate yet another new way to leverage vocal biomarkers for better health outcomes.
The 245 study participants were asked to record their voices six times a day for two weeks speaking into a proprietary mobile app developed by Klick scientists, which detected high blood pressure with accuracy of up to 84 percent for women and 77 percent for men. The app uses machine learning to analyze hundreds of vocal biomarkers that are imperceptible to the human ear, including the variability in pitch (fundamental frequency), the patterns in the distribution of speech energy (Mel-frequency cepstral coefficients) and the sharpness of sound changes (spectral contrast).
“By using different classifications and building gender-based predictive models, we have discovered a more accessible way to detect hypertension, which we hope will lead to earlier intervention for this widespread global health problem. Hypertension can lead to a number of complications, from heart attacks and kidney problems to dementia,” said Yan Fossat, senior vice president of Klick Labs and principal investigator of the study.
More accessible screening for the ‘silent killer’
The World Health Organization (WHO) calls hypertension the ‘silent killer’ and is a global public health problem affecting more than 25 percent of the world’s population. Half are unaware of their condition, and more than 75 percent of people diagnosed live in low- or middle-income countries.
Conventional methods of measuring blood pressure (and accordingly identifying hypertension) include the use of an arm cuff (sphygmomanometry) or an automatic blood pressure measuring device. However, these methods may require technical expertise and specialized equipment and may not be easily accessible to people in underserved areas.
This study marks Klick Labs’ first attempt to use voice technology to identify conditions beyond diabetes, as the company expands its research to assess the effectiveness of its AI algorithms in detecting and managing a broader range of health conditions. Klick Labs has been working with hospitals, academic institutions and public health authorities worldwide since research showed that voice analysis combined with AI can accurately screen for type 2 diabetes in Mayo Clinic Procedure: Digital Health in October 2023). Last weekScientific reports published another study from Klick Labs, which confirmed the link between blood glucose levels and voice pitch.
Voice technology has the potential to exponentially transform healthcare, making it more accessible and affordable, especially for large, underserved populations. Our ongoing research increasingly demonstrates the significant promise of vocal biomarkers in detecting high blood pressure, diabetes and a growing list of other health conditions.”
Jaycee Kaufman, Klick Labs research scientist and co-author of the study
Source:
Magazine reference:
Taghibeyglou, B., et al(2024) Machine learning-assisted hypertension screening using acoustic speech analysis: model development and validation. IEEE Access, doi.org/10.1109/ACCESS.2024.3443688.