Scientists in the United States have developed a tool for detecting signs of coronary artery disease through speech patterns, which they believe could aid in a more accurate diagnosis.

Coronary artery disease is the most common type of heart disease. It affects 18.2 million people in the United States aged 20 years or older.

Researchers from the Mayo Clinic in Rochester, Minnesota, in collaboration with a researcher from the University of Tel Aviv in Israel, have demonstrated that the analysis of voice samples using artificial intelligence can aid in predicting the risk of coronary artery disease and its complications, such as a heart attack or chest pain.

The use of voice analysis to diagnose coronary artery disease early could potentially enhance patient outcomes. This technology uses a mobile application to gather speech samples and could be a cost-effective and noninvasive way to assess persons at risk of coronary artery disease remotely.

The analysis of voice samples could be utilized as a screening tool to identify people who need more attention for coronary artery disease events.

“We’re not suggesting that voice analysis technology would replace doctors or replace existing methods of healthcare delivery,” says the study’s co-author, Dr. Jaskanwal Deep Singh Sara “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.”

The research was presented at the American College of Cardiology meeting in Washington, DC, on April 2-4, 2022, and was published in the Mayo Clinic Proceedings at the same time.

Predicting CHD risk

The buildup of plaque in the inner walls of coronary arteries, which feed blood to the heart, is known as coronary artery disease. Plaque builds up in these arteries, restricting or obstructing them and limiting blood flow to the heart. Angina or chest pain, heart failure, and heart attack are all complications associated with coronary artery disease.

The authors of this study have previously examined the voice characteristics of people with coronary artery disease to those of healthy people, such as amplitude and pitch. They discovered that specific vocal traits were more likely to be seen in patients with coronary artery disease in prior research.

The goal of this study was to see if these previously identified vocal characteristics could predict the risk of coronary artery disease.

Coronary artery disease risk

In this study, 108 people were asked to get coronary angiography, which uses X-rays to check the condition of the coronary arteries.

Using a smartphone application, the researchers acquired voice recordings from each subject. Three separate vocal samples were requested from the patients: reading a text, describing an unpleasant event, and reporting a positive one.

The researchers employed ai algorithms to analyze the audio recordings and extract vocal traits that had previously been linked to coronary artery disease in another study. Using these vocal traits, they created a single biomarker score for each participant. After that, the subjects were divided into two groups based on whether they had a low or high biomarker score.

The researchers discovered that patients with a higher biomarker score were 2.6 times more likely to experience or be hospitalized for symptoms linked with coronary artery disorders, such as chest discomfort or a heart attack, after a two-year follow-up period.

Furthermore, people with higher biomarker scores had a 3.1 greater chance of being diagnosed with coronary artery disease during a future angiography or having a positive exercise stress test, which is a risk factor for coronary artery disease.

The future of speech analysis

In the emerging field of telemedicine, voice analysis has a lot of promise. “The future of voice analysis and human health is teeming with countless opportunities,” Dr. Alan Sugrue, a Mayo Clinic researcher, wrote in an editorial. “Because all telecommunications today are generally digital, voice analysis could be easily integrated into current technological platforms (such as a smartphone) with either analysis by software on the platform or transmission of digital voice recordings to a central procession area.”

“Artificial intelligence has the potential to learn your voice,” he added, “and its myriad variations and thereby determine whether substantial and subtle changes may correlate with disease that is either subacute or acute.”

Study limitations

The artificial intelligence platform utilized in the study was initially taught using voice samples obtained from individuals in Israel, according to the researchers.

Despite the fact that the current study used voice samples from English-speaking people in the Midwest, the scientist advised that more research is needed to see if the findings can be applied to a bigger and more diversified demographic of people who speak different languages.

Security and privacy concerns related to this new technique, like with existing telehealth technologies, must be addressed before widespread usage.

Image Credit: Getty

You were reading: Doctors Can Now Diagnose Heart Patients Just by Listening to Their Voice