Researchers at the Mayo Clinic in the US found that when people have worrisome heart problems, it can be detected in their voices.
Although the vocal change is too subtle for humans to hear; Scientists have created an artificial intelligence algorithm that can pick up small differences in speech, according to the Telegraph.
In a study group of 108 people at high risk of heart disease, nearly six in 10 of those who scored high on an audio risk score ended up in hospital within two years, compared to just three in 10 of those with the lowest score.
People with high scores were also 2.6 times more likely to have major problems associated with coronary artery disease, and three times more likely to have plaque buildup in the arteries, compared to those with low scores.
“We can’t hear these special features ourselves,” said Dr. Jaskanwal Deep Singh Sara of the Mayo Clinic, lead author of the study.
“This technology uses machine learning to identify something that cannot easily be quantified to us using our human brains and ears.”
The researchers hope that the technology will be able to monitor people remotely and report which patients are most at risk.
“Telemedicine is non-invasive, cost-effective, and has become increasingly important during the pandemic,” Sara added.
“We are not suggesting that voice analysis technology will replace physicians or current approaches to healthcare delivery, but we believe there is a significant opportunity for voice technology to serve as an adjunct to current strategies,” he said.
“Providing an audio sample is very intuitive and enjoyable even for patients, and can become a scalable way for us to enhance patient management,” the doctor noted.
The study marks the first time that audio analysis has been used to predict heart health.