Published on
updated on
Reading 2 min.
For the past twenty years, the prevalence of diabetes (type 1 and type 2) has continued to increase worldwide. It is estimated that by 2050, more than 1.3 billion people will suffer from this chronic disease, which can cause serious complications if left untreated. To better diagnose it, Canadian researchers believe that doctors should pay more attention to their patients’ voices.
Scientists at Klick Labs have discovered a surprising correlation between blood sugar levels and the fundamental frequency of the voice. They came to this discovery after conducting an experiment involving 505 participants, who are non-diabetic, prediabetic or type 2 diabetic. As a reminder, type 2 diabetes accounts for most cases of diabetes. It is caused by a decrease in the sensitivity of cells to insulin, a hormone of pancreatic origin that regulates blood sugar.
For the needs of their studythe researchers equipped the volunteers with continuous glucose sensors. They also recorded their voices several times a day for two weeks. It appeared that the higher the blood sugar level, the higher the pitch of the voice. In detail, an increase of 1 mg/dL of glucose in the body causes a 0.02 Hz increase in vocal frequency. This change is imperceptible to the ear but it is detectable by sensitive audio analysis.
Surprisingly, this relationship was observed not only in people with diabetes, but also in those with normal blood sugar levels. The authors of the study, whose findings are published in the journal Scientific Reports, speculate that this phenomenon may be related to the impact of glucose on the vocal folds (commonly known as vocal cords). High blood sugar could potentially cause subtle changes in vocal cord tension or hydration, leading to increased pitch.
This discovery could revolutionize the way people with diabetes monitor their blood sugar. The researchers believe that it would be possible to design a voice application that would allow diabetics to measure their blood sugar levels using their voice. A much less invasive method of self-monitoring than those currently available.[Cela] could be a game-changer for the estimated 463 million people worldwide living with type 2 diabetes” says Jaycee Kaufman, lead author of the study, in a press release.
The research adds to a growing body of research that shows voice is a good indicator of a person’s health. Over the past decade, scientists have used artificial intelligence and machine learning to detect vocal biomarkers for a range of conditions, including dementia, depression, and even heart disease.
Slideshow: Diabetes: 10 tips to avoid complications