AI and 10 Seconds of Voice can Screen for Diabetes

Diabetes is a chronic disease that affects millions of people worldwide. It is characterized by high blood sugar levels, which can lead to serious health problems such as heart disease, stroke, and blindness. Early detection and treatment of diabetes is essential to preventing these complications.

Artificial intelligence (AI) has the potential to revolutionize the way diabetes is detected. AI-powered systems can be trained to identify patterns in medical data that are associated with diabetes, even in people who do not have any obvious symptoms. 

One approach is to use AI to analyze medical images, such as retinal scans and CT scans. Another approach is to use AI to analyze electronic health records. AI can also be used to develop wearable devices that can monitor patients’ blood sugar levels and other health markers. This data can be relayed to a healthcare provider, who can use it to track the patient’s progress and identify any early signs of diabetes.

In this article, an AI algorithm uses 6 to 10 seconds of voice to detect type 2 diabetes. More than 18,000 recordings were analyzed for over 14 different acoustic features, which were different among diabetics and non-diabetics. Participants also provided basic health data like age, height, and weight. Detection was 89% accurate for diagnoses in women and 86% for men.

The full study was published in “Mayo Clinic Proceedings: Digital Health,”

The new study, published in Mayo Clinic Proceedings: Digital Health, outlines how scientists used six to 10 seconds of people’s voice, along with basic health data, including age, sex, height, and weight, to create an AI model that can distinguish whether that individual has Type 2 diabetes. The model has 89 percent accuracy for women and 86 percent for men.

View referenced article