AI technology has been successfully used to predict if someone is likely to suffer from heart problems in the future.
In a breakthrough study presented at the American College of Cardiology’s 71st Annual Scientific Session, researchers revealed that people with a ‘high voice biomarker score were 2.6 times more likely to suffer major problems associated with coronary artery disease (CAD)’.
It’s definitely an exciting field, but there’s still a lot of work to be done.
Dr Jaskanwal Deep Singh Sara
And the scientists behind the AI-based algorithm technology used to show this believe it will soon have a transformative impact on remote health care.
“Telemedicine is non-invasive, cost-effective and efficient and has become increasingly important during the pandemic,” said Dr Jaskanwal Deep Singh Sara, a cardiology fellow at Mayo Clinic and the study’s lead author. “We’re not suggesting that voice analysis technology would replace doctors or replace existing methods of health care delivery, but we think there’s a huge opportunity for voice technology to act as an adjunct to existing strategies. Providing a voice sample is very intuitive and even enjoyable for patients, and it could become a scalable means for us to enhance patient management.”
It is the first time voice analysis has been used to gauge CAD outcomes in patients who went on to be monitored after an initial screening.
More than 100 patients took part in the study, with each asked to record three 30 second audio samples using the ‘Vocalis Health smartphone application’. The algorithm analysed them for features including ‘frequency, amplitude, pitch and cadence’ against a set of 10,000 plus voice samples. Features closely linked to CAD, pinpointed in earlier research, were fed into this new study to generate a score between -1 and 1: with two-thirds returning a low score, and the rest a high score.
“We can’t hear these particular features ourselves,” Sara said. “This technology is using machine learning to quantify something that isn’t easily quantifiable for us using our human brains and our human ears.”
Those who took part in the study were tracked for two years, and nearly 60% of those with a high voice biomarker score went to hospital in this time with ‘chest pain or suffered acute coronary syndrome’ compared to less than one-third of those from the low biomarker group.
The reason certain voice patterns are indicative of potential heart problems is unclear and Sara says more needs to be done to assess whether the technology is scalable across languages, as this study only involved English speakers in the Midwestern U.S.
Sara added: “We have to know the limitations of the data we have, and we need to conduct more studies in more diverse populations, larger trials and more prospective studies like this one.”