Doctors can tell whether you have cardiovascular disease by listening to your VOICE

Doctors may be able to spot heart disease in patients by listening to the way they speak, a study suggests. 

A computer algorithm was able to detect those most at risk of the condition by looking for clues in voice recordings. 

Tiny changes to the frequency, tone or pitch of someone’s delivery – which are undetectable to the human ear – holds clues to heart health, the researchers said. 

While the exact reason why the voice appears to be affected by health of the heart is unclear medics believe it is related to how the nervous system regulates unconscious body functions like the voice box, blood pressure, and heart rate. 

Researchers found people who scored ‘high’ in the AI’s voice assessment were more than two-and-a-half times as likely to suffer from complications from cardiovascular disease such as a heart attack. 

While not currently a substitute for a check-up by a human health professional, the researchers hope it could one day be another tool in spotting people at risk of heart disease, one of Britain’s biggest killers.     

US researchers have trained an algorithm to spot tiny changes to the human voice which could be an indicator of heart disease 

Researchers from the Mayo Clinic in the US tested an algorithm trained to analyse over 80 aspects of the human voice, such as amplitude, pitch and cadence.

They asked 108 patients, average age of 60, who had undergone a heart scan for coronary artery disease to record three 30-second samples of their voice on a smartphone.

Coronary artery disease (CAD) clogs up the blood vessels and can lead to angina, strokes or heart attacks

Coronary artery disease occurs when the major blood vessels that supply the heart with oxygen and nutrients become damaged.

CAD affects more than 1.6million men and one million women in the UK, and a total of 15million adults in the US. 

It is usually due to plaque and inflammation.

When plaque builds up, it narrows the arteries, which decreases blood flow to the heart.

Over time this can cause angina, while a complete blockage can result in a heart attack.

Many people have no symptoms at first but as the plaque builds up they may notice chest pains or shortness of breath when exercising or stressed. 

Other causes of CAD include smoking, diabetes and an inactive lifestyle. 

It can be prevented by quitting smoking, controlling conditions like diabetes or high blood pressure, staying active, eating well and managing stress. 

Drugs can help to lower cholesterol, while aspirin thins the blood to reduce the risk of clots.

In severe cases, stents can be put into the arteries to open them, while coronary bypass surgery creates a graft to bypass the blocked arteries using a vessel from another part of the body.

Source: Mayo Clinic 

The first sample was reading from a script whereas for the other two exercises were asked to speak freely about a positive and a negative experience. 

Each person was then scored by the algorithm as being at ‘high risk’ or ‘low risk’ of heart disease. 

The researchers, who will present their findings officially at the American College of Cardiology’s 71st Annual Scientific Session in Washington DC next month, then tracked the participants for two years.  

The researchers found 58.3 per cent of the high scorers visited hospital for chest pain or a heart attack in that period compared to just 30.6 per cent of low scorers. 

This meant that high scorers were 2.6 times as likely to suffer what the medics considered major problems from coronary artery disease compared to low scorers. 

It is not clear what age the patients in the study were. 

Coronary artery disease is when major blood vessels which supply the heart become narrowed by the build-up of fatty deposits.

It can lead to heart attacks when these deposits rupture and lead to a blood clot which blocks the blood supply to the organ. 

A high-fat diet, smoking, and conditions like high blood pressure and diabetes can increase the risk of developing coronary artery disease.

Lead author of the study Dr Jaskanwal Sara, a cardiologist at the Mayo Clinic, said if developed further voice analysis could provide a non-invasive and cost effective way of identifying patients at risk of coronary artery disease. 

‘We’re not suggesting that voice analysis technology would replace doctors or replace existing methods of health care delivery,’ he said.

‘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.’

Dr Sara says much more research needs to be done on using voice analysis to assess heart health before it could be used clinically.  

In particular he said further studies needed to determine if the results could be replicated in different languages and accents.

It is not the first time that patient voice patterns have used to assess heart health, however in contrast to most recent study that research was done retrospectively after patients suffered problems like heart failure.

Similar studies have also tried to use subtle changes in vice patterns to detect conditions like Parkinson’s and Alzheimer’s disease and even Covid infection.  

Coronary artery disease affects more than 1.6million men and one million women in the UK, and a total of 15million adults in the US. It kills 64,000 Britons and 360,900 Americans a year. 

For all the latest health News Click Here 

Read original article here

Denial of responsibility! TechAI is an automatic aggregator around the global media. All the content are available free on Internet. We have just arranged it in one platform for educational purpose only. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials on our website, please contact us by email – [email protected]. The content will be deleted within 24 hours.