AI detects hypertension in voice recordings

Researchers have used artificial intelligence (AI) to identify signs of hypertension in audio recordings, sharing their findings in IEEE Access.[1]

The group used a proprietary mobile app developed by Klick Labs, a research and development division of Canada-based Klick Health. Nearly 250 patients recorded their voices into the app up to six times per day for two weeks. The machine learning-powered app was trained to evaluate voices for hundreds of biomarkers, including many that can’t even be detected by the human ear. 

Overall, when working to identify patients with a systolic blood pressure (SBP) ≥ 135 mmHg or a diastolic blood pressure (DBP)  ≥ 85 mmHg, the app was associated with an accuracy of 84% for women and 77% for men. For a separate threshold—a SBP of ≥ 140 mmHg or DBP ≥ 90  mmHg—the AI was less accurate for women (63%), but more accurate for men (86%). 

“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,” principal investigator Yan Fossat, a senior vice president of Klick Labs, said in a statement. “Hypertension can lead to a number of complications, from heart attacks and kidney problems to dementia.”

Other ongoing research at Klick Labs has been focused on how the company’s AI models may be able to identify signs of type 2 diabetes. The latest results from that project were published in Mayo Clinic Proceedings: Digital Health in October 2023.

“Our ongoing research increasingly demonstrates the significant promise of vocal biomarkers in detecting hypertension, diabetes, and a growing list of other health conditions,” co-author Jaycee Kaufman, a research assistant with Klick Labs, said in the same statement. 

The team’s analysis was funded in full by Klick Health. 

Click here to read the full study.

Michael Walter
Michael Walter, Managing Editor

Michael has more than 18 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.

Around the web

Ron Blankstein, MD, professor of radiology, Harvard Medical School, explains the use of artificial intelligence to detect heart disease in non-cardiac CT exams.

Eleven medical societies have signed on to a consensus statement aimed at standardizing imaging for suspected cardiovascular infections.

Kate Hanneman, MD, explains why many vendors and hospitals want to lower radiology's impact on the environment. "Taking steps to reduce the carbon footprint in healthcare isn’t just an opportunity," she said. "It’s also a responsibility."