Medical scientists have developed a potentially revolutionary and highly convenient method for detecting Type 2 diabetes that could identify the disease simply by analysing a patient’s voice, without the need for a blood sample.
According to scientists, diabetes can cause subtle changes in a person’s voice frequency, flexibility and vocal cords that are not detectable by the human ear but can be quickly identified by an AI system.
Patients only need to speak a sentence for six to 10 seconds on their smartphone, after which an AI model analyses the voice sample to determine whether the person has diabetes. The test reportedly delivers results with an accuracy of around 89%.
The technology could prove highly useful for millions of people with diabetes, potentially saving time and money while enabling painless testing from home.
Millions of people worldwide remain unaware that they have the disease, and the test could help detect this “silent” condition at an early stage.
The AI tool can diagnose diabetes in women by the pitch of their voice, the amount of deviation from that pitch, and by relative average fluctuations in pitch in a single captured recording.
For males, the authors describe an analysis of intensity, or amplitude, in the voice, as well as relative average perturbations in pitch for diagnosing type 2 diabetes.
Study reveals that one in two, or 240 million adults living with diabetes worldwide remain unaware they have the condition and nearly 90 percent of diabetic cases are Type 2 diabetes. The most common diagnostic tests for kids and Type 2 diabetes comprise glycated hemoglobin (A1C), along with the fasting blood glucose (FBG) test and the OGTT–all which include a trip to a healthcare provider for patients.
Also Read: Alzheimer’s new study raises hope of reversing memory loss
