AI can detect type 2 diabetes – just by voice

A new AI is supposed to detect type 2 diabetes with an accuracy of up to 71 percent – using only the voice. The method could fundamentally change the diagnosis.

Medicine is making great progress as part of digitalization. Researchers recently developed a new method to detect type 2 diabetes using voice alone. An algorithm uses artificial intelligence to analyze a person's voice to obtain information about the disease. ,

According to research results, the accuracy is up to 71 percent for men and up to 66 percent for women. What's special about it is that the method is non-invasive and could make diabetes screenings easier and more accessible. To do this, the AI ​​analyzes various characteristics of the voice such as pitch and intensity. At the same time, the algorithm receives general health data such as age, gender and body mass index (BMI).

AI detects type 2 diabetes – through changes in the voice

The idea is that health problems such as diabetes can cause changes in the voice. For the study, the researchers asked 607 people to speak and record a short text on their smartphone or laptop.

The AI ​​system then evaluated the data to distinguish between people with and without diabetes. The advantage of this technology is that it is quick and easy to use, unlike traditional methods, which often cost time and money. Because current diabetes tests often include blood tests.

The diagnosis is more reliable, especially in older people

Voice analysis could therefore close a major gap and help detect diabetes earlier worldwide. People over 60 and people with high blood pressure are particularly expected to benefit from the method, as the AI ​​is particularly precise for them.

The research is still in its early stages and further studies are needed to improve the method. Nevertheless, voice analysis could play an important role in the early detection of type 2 diabetes in the future and help millions of people to better monitor their health.

Also interesting: