AI can detect high blood pressure by listening to your voice

Experts at Klick Labs have developed a novel, non-invasive technique that taps into the health screening potential of our voices. The researchers have demonstrated that it is possible to detect chronic high blood pressure (hypertension) with impressive accuracy using just a person’s voice.

With its effortless simplicity, the new method could lead to substantial advancements in early detection of hypertension, a widespread health condition.

Voice biomarkers and blood pressure

In this unique study, 245 individuals were assigned a straightforward task. Over two weeks, they recorded their voices multiple times a day using a specialized mobile app.

This app, a homegrown project from the Klick scientists, works on the principles of machine learning. The voice technology has exhibited an impressive 84 percent accuracy for females and 77 percent for males in detecting high blood pressure.

The magic lies in its unique capability to analyze vocal biomarkers that escape human ears. This includes pitch variations, patterns in speech energy distribution, and the distinctness in sound alterations.

High blood pressure and voice recordings

Yan Fossat is the senior vice president of Klick Labs and principal investigator of the study.

“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 Fossat.

“Hypertension can lead to a number of complications, from heart attacks and kidney problems to dementia.”

Battle against the silent killer

Hypertension, referred to as the “silent killer” by the World Health Organization (WHO), is a global health concern affecting over a quarter of the world’s population.

Alarmingly, half of these people are not even aware of their condition. Furthermore, over 75 percent of those diagnosed with hypertension live in low or middle-income countries.

Traditionally, blood pressure is measured using an arm cuff or an automatic device, methods that need specialized equipment and expertise. Unfortunately, these are often inaccessible for people in disadvantaged areas.

“Early diagnosis and behavioral interventions have been shown to mitigate morbidity and mortality associated with this condition,” noted the researchers.

“However, conventional methods of measuring blood pressure and accordingly identifying hypertension, such as sphygmomanometry, require technical expertise and may not be readily accessible, particularly in remote or underserved areas.”

Broader implications of the research

The introduction of voice-based high blood pressure detection extends beyond individual health assessments; it has significant implications for public health strategies.

With the ability to uncover undiagnosed cases of hypertension through a simple app, healthcare systems can redirect resources toward prevention and education initiatives.

The technology could empower individuals with the information they need to seek further evaluation and treatment. This is particularly the case in regions where traditional access to healthcare is limited.

By promoting greater awareness and early intervention, communities could effectively mitigate the risks associated with hypertension, ultimately leading to improved health outcomes and reduced healthcare costs over time.

Beyond blood pressure detection

Klick Labs is not a newcomer in the field of health tech. With a track record of using voice technology for detecting conditions like diabetes, the lab is continually expanding its research base.

Collaborations with numerous hospitals, academic institutions, and public health authorities globally are a testament to the lab’s commitment to healthcare advancements.

Klick Labs previously demonstrated the effectiveness of AI algorithms combined with voice analysis in accurate screening for Type 2 diabetes. The research was published in Mayo Clinic Proceedings: Digital Health in October 2023.

The lab also identified a link between blood glucose levels and voice pitch. The research was published last week in the journal Scientific Reports.

Significance of the study

“Voice technology has the potential to exponentially transform healthcare, making it more accessible and affordable, especially for large, underserved populations,” said Jaycee Kaufman, Klick Labs research scientist.

“Our ongoing research increasingly demonstrates the significant promise of vocal biomarkers in detecting hypertension, diabetes, and a growing list of other health conditions.”

By subtly wearing the cloak of technology, healthcare is quietly tiptoeing into the future. Only time will tell how these advancements will shape our lives.

The study is published in the journal IEEE Access.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–