Researchers at Klick Labs have unveiled an innovative method for detecting chronic high blood pressure, or hypertension, using just a person’s voice. This groundbreaking non-invasive technique could transform how we screen for and manage this “silent killer,” which affects over 25 percent of the global population. Their study offers a promising glimpse into the future of early hypertension detection, making health monitoring more accessible and effective.
The World Health Organization (WHO) often refers to hypertension as a “silent killer” due to its asymptomatic nature and the serious health risks it poses. Traditional blood pressure measurement methods, like arm cuffs or automatic devices, are often inaccessible in low- and middle-income countries, where technical expertise and resources may be limited.
The intensity and energy in speech might reflect cardiovascular function. Alterations in these patterns can be associated with stress or physical strain that correlates with hypertension. Subtle alterations in voice sounds, such as tremors or fluctuations, could be indicative of underlying health conditions, including high blood pressure.
The study involved 245 participants who recorded their voices up to six times a day over two weeks using a mobile app developed by Klick Labs. This app employs advanced machine learning algorithms to analyze subtle vocal features such as pitch variability, speech energy patterns, and sound changes, accurately predicting hypertension. The results are impressive: the app achieved up to 84 percent accuracy for women and 77 percent for men.
Yan Fossat, senior vice president of Klick Labs and principal investigator of the study, highlighted the importance of their findings. “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. Hypertension can lead to complications ranging from heart attacks and kidney problems to dementia,” he explained.
Klick Labs’ voice-based technique offers a solution that is not only easier but also more accessible. This study marks the lab’s first major venture into using voice technology for health conditions beyond diabetes. Their previous research demonstrated that voice analysis combined with AI could effectively screen for Type 2 diabetes, as published in Mayo Clinic Proceedings: Digital Health in October 2023. A recent study in Scientific Reports also confirmed the link between blood glucose levels and voice pitch.
Jaycee Kaufman, a research scientist at Klick Labs and co-author of the study, emphasized the potential impact of this technology. “Voice technology has the potential to exponentially transform healthcare, making it more accessible and affordable, especially for large, underserved populations,” she stated.
As Klick Labs continues to explore the potential of vocal biomarkers, this pioneering work in voice-based health monitoring could pave the way for new, cost-effective tools to screen for a variety of conditions, making early intervention and better health outcomes a reality for millions around the world.
Article written by Sujita Sinha
11/09/2024
Source:
Interesting enginerring
https://interestingengineering.com/health/ai-detects-high-blood-pressure-through-voice?utm_source=substack&utm_medium=email