Researchers at the Mayo Clinic believe that there may be a relationship between voice characteristics and heart disease, meaning that doctors might someday use voice-analyzing software as a non-invasive, complementary diagnostic tool.
Today, the Mayo Clinic released results of a study carried out with Beyond Verbal, an Israel-based voice analytics company, that used a smartphone app to measure their voice signal prior to a coronary angiograph. The double-blind study, which included 120 patients (who were referred for the heart disease test) and corresponding controls, identified one voice feature associated with a 19-fold increased likelihood of coronary artery disease. The researchers also identified 13 voice features that were associated with coronary artery disease, with the strongest such feature observed when patients were requested to record their voice while describing a negative experience.
“This study suggests a potential relationship between voice characteristics and CAD,” the researchers wrote on the poster to be presented at American Heart Association Scientific Sessions. “Voice features analysis holds the potential to assist physicians in estimating the pre-test probability of CAD among patients presenting chest pain, especially in the setting of telemedicine.”
Beyond Verbal, which was founded in 2012, launched its Beyond Wellness API in 2014. The software turns any smartphone or mic-equipped wearable device into an emotional wellbeing sensor using technology that doesn’t consider the actual content or context of spoken word, but instead studies intonation in the voice. The company has two free, consumer-facing apps, Moodie and Empath, and one for clinicians called Beyond Clinic. The company presents its products as a means of gauging emotions for a variety of situations – workplace wellness, market research, even a recent interview between Donald Trump and Megyn Kelly.
In September, the company launched a research platform to leverage its software into health with the goal of identifying physiological markers through voice that may indicated various health related issues. While the company has experience with voice analysis on conditions that more plainly affect vocal acoustics – such as Parkinson’s or other neurocognitive conditions – this research with the Mayo Clinic is the first to demonstrate the vocal indicators of purely physical disease.
“This study has been underway for two years, and it took us awhile to understand the meaning from it, but we feel like there is real substance there,” Yuval Mor, CEO of Beyond Verbal told MobiHealthNews in an interview. “Finding correlations in voice features to physical symptoms means there could be continuations in other areas.”
The vocal features that indicate heart disease, Mor said, are not audible by the human ear alone. “What it sounds like specifically is not something that can be articulated, it’s not something that the human ear can detect,” he said. “It’s similar to eyesight in that we can see a certain spectrum, but much more exists.”
Mor said the Mayo Clinic research presents an opportunity to move into many therapeutic areas and potentially develop an app that can alert people if they may be at risk of a certain condition based on their voice. “This opens the door for us to continue research on the cardio side as well as begin multi-site, multi-language studies,” Mor said.