A new study has revealed that an AI-based tool could help detect type 2 diabetes in seconds by analyzing subtle changes in the way people speak.
Hot Topics
About half of Libyans drink contaminated water What is the scientific reason?
Mauritania's blue treasure is in danger Will the map of fish in the Atlantic be redrawn?
The Citrus Secret Everyone's Talking About: Burn More, Crave Less & Feel Great Naturally
The researchers say the technology could "open a new path for screening for diabetes," especially for people who do not undergo regular health checks, while emphasizing that it does not replace the blood tests currently used to diagnose the disease.
Researchers at the technology company "Thymia" and "RMIT" University in Melbourne, Australia, developed the tool, which is based on analyzing changes in voice and speech associated with type 2 diabetes, including increased hoarseness, vocal strain, and difficulty controlling breathing while speaking.
Researchers believe these changes may be linked to the effect of high blood sugar levels on the vagus nerve, which is involved in controlling the laryngeal muscles. Diabetics are also more prone to gastroesophageal reflux disease (GERD), which can irritate the vocal cords and cause hoarseness, in addition to the impact of certain lung function disorders on airflow during speech.
The researchers trained the tool using more than 63,000 voice samples from over 21,000 people in the UK and the US. They then tested it using 20-second audio recordings of participants reading aloud.
The researchers found that the model assigned higher risk scores to people who reported having type 2 diabetes in 80% of cases. In another analysis of 801 people who underwent home blood tests within three months of recording their voices, the rate was 75%.
Although the tool performed well across different age groups and genders, it declined when analyzing the voices of Black participants, and researchers suggest that the low number of participants from this group is one of the reasons for this.
The delayed diagnosis of type 2 diabetes is a significant problem, as its symptoms may appear gradually, such as fatigue and excessive thirst, while some people may not undergo the routine tests that help detect the disease.
Jedri Sebukaite, a researcher at the company "Thymia," said that the technology "has the potential to change the shape of screening and early detection processes," explaining that collecting a voice sample via phone or app could help reach people who do not undergo regular health checks.
Sibokaite stressed that the device is not a substitute for blood testing, saying: "Our model opens up a new avenue for detecting diabetes. It is not a substitute for blood testing, and in no way should it discourage anyone who thinks they need to be tested from getting tested."
In the next phase, the researchers plan to test the model in clinical settings and study its effectiveness among different segments of society before using it more broadly.
what is your opinion on this news ?do let us know in the comments on tha comment box
if you liked this news article please share on friends & family & don't forget to follow on website & social media
