People could be diagnosed with diabetes using little more than a voice recording from their phone, promising new research has suggested.
Experts have long feared millions of Brits with the condition — which causes blood sugar levels to become too high — are going undiagnosed.
But audio samples of patient’s voices lasting just 25 seconds, along with basic health data like age, sex, height and BMI could determine whether someone is diabetic.
Scientists, who tested the AI model on more than 600 adults, found it was accurate in more than two thirds of cases.
Charities and experts today welcomed the ‘innovative’ tool but cautioned further research was needed.
Experts have long feared millions of Brits with the condition — which causes blood sugar levels to become too high — are going undiagnosed. But audio samples of just 25 seconds, along with basic health data like age, sex, height and BMI could determine whether someone is diabetic
Almost 4.3 million people were living with diabetes in 2021/22, according to the latest figures for the UK. And another 850,000 people have diabetes and are completely unaware of it, which is worrying because untreated type 2 diabetes can lead to complications including heart disease and strokes
Abir Elbeji, an expert in digital health at the Luxembourg Institute of Health and study lead author, said: ‘Most current methods of screening for type 2 diabetes require a lot of time and are invasive, lab-based, and costly.
‘Combining AI with voice technology has the potential to make testing more accessible by removing these obstacles.
‘This study is the first step towards using voice analysis as a first-line, highly scalable type 2 diabetes screening strategy.’
In the UK, more than 90 per cent of adults with diabetes have type two — but many go for years without realising because symptoms can be general or non-existent.
To be tested for the condition, people usually require a GP visit and urine and blood tests.
In the study, the researchers analysed 607 recordings to identify acoustic features that differentiated non diabetics from diabetics.
All were asked to read sentences provided directly from their phone or laptop.
Using signal processing, they were then able to detect subtle changes in pitch, tone and intensity that are imperceptible to the human ear.
One advanced AI technique captured up to 6,000 detailed vocal characteristics. Another focused on 1,024 key features.
The model had a 66 per cent accuracy rate for women, with 71 per cent among men.
The model performed even better in females aged 60 years or older and in people with hypertension, the researchers added.
Responding to the findings, Dr Lucy Chambers, Head of Research at Diabetes UK, said: ‘Getting a prompt and accurate diagnosis is crucial for preventing the serious and life-limiting complications of type 2 diabetes.
‘Unfortunately, symptoms can be easily overlooked, and about 1.2 million people in the UK are currently living with undiagnosed type 2 diabetes.
‘Using AI to develop convenient and cost-effective type 2 diabetes screening methods will help identify more people who need treatment and support, ultimately improving their quality of life and reducing their risk of long-term diabetes complications.
‘We look forward to further research on innovative AI voice analysis tools for diabetes screening.’
The research will be presented tomorrow at the Annual Meeting of The European Association for the Study of Diabetes (EASD) in Madrid.
Type 2 diabetes occurs when the body doesn’t make enough insulin or the insulin it makes doesn’t work properly.
This hormone is needed to bring down blood sugar levels.
Having high blood sugar levels over time can cause heart attacks and strokes, as well as problems with the eyes, kidneys and feet.
Sufferers may need to overhaul their diet, take daily medication and have regular check-ups.
Symptoms of the condition, which is diagnosed with a blood test, include excessive thirst, tiredness and needing to urinate more often. But many people have no signs.
Almost 4.3million people were living with diabetes in 2021/22, according to the latest figures for the UK.
Approximately 90 per cent of diabetes cases are type 2 diabetes, which is linked with obesity and is typically diagnosed in middle age, rather than type 1 diabetes, a genetic condition usually identified early in life.
