New AI Tool Identifies Diabetes Using Voice Analysis

Researchers at the Luxembourg Institute of Health (LIH) Deep Digital Phenotyping Research Unit have developed a voice-based artificial intelligence algorithm that can accurately detect Type 2 Diabetes (T2D). This non-invasive and cost-effective method could make diabetes screening accessible to millions, especially in underserved communities.

A team of researchers led by Abir Elbeji and Dr. Guy Fagherazzi from the Luxembourg Institute of Health’s Deep Digital Phenotyping Unit has developed an original approach that relies on distinguishing subtle changes in one’s voice. 

Using advanced machine learning techniques, the team identified vocal biomarkers that correlate with T2D, offering a glimpse into the future of non-invasive, scalable, and affordable health screening to diagnose T2D. Using artificial intelligence (AI) algorithms, the team achieved a predictive accuracy comparable to the risk score widely used by the American Diabetes Association (ADA). 

“This research represents a major step in diabetes care. By combining AI with digital phenotyping, we are ushering in a more inclusive and cost-effective approach to early diagnosis and prevention. The ability to screen for diabetes using a simple voice recording could dramatically improve healthcare accessibility for millions of people around the world,” said Dr. Guy Fagherazzi.

The study, published the journal PLOS Digital Health and part of the larger Colive Voice program, analyzed speech recordings of over 600 participants in the United States. Detection rates were noted better in key demographics, including women over 60 and individuals with hypertension.

In the future, the researchers aim to refine the algorithm for early detection of prediabetes and undiagnosed T2D cases. Plans are also underway to expand the program to other populations and languages.