Vocal analysis could revolutionise type 2 diabetes diagnosis – with AI screening

Researchers have developed a voice-based artificial intelligence (AI) algorithm capable of detecting type 2 diabetes with “remarkable accuracy”.

By analysing subtle vocal changes, researchers have developed a non-invasive and cost-effective method that 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 researchers identified vocal biomarkers that correlate with type 2 diabetes, offering a glimpse into the future of non-invasive, scalable, and affordable health screening where the condition could be diagnosed using a simple voice recording.

The study findings were recently published in PLOS Digital Health and part of the larger Colive Voice programme

Researchers analysed speech recordings of more than 600 participants in the United States. Using artificial intelligence (AI) algorithms, the team achieved a predictive accuracy comparable to the risk score widely used by the American Diabetes Association (ADA).

Notably, researchers found improved detection rates in key demographics, including women aged over 60 and individuals with hypertension.

Type 2 diabetes is one of the most pressing public health problems, with an estimated 400 million undiagnosed cases worldwide. The consequences of delayed diagnosis are severe and can result in further complications like cardiovascular disease and neuropathy, leading to higher healthcare costs and increased mortality.

Current screening methods rely on blood tests, which can be costly and logistically difficult in settings with limited resources.

Dr Fagherazzi said: "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."

In future studies, the researchers aim to refine the algorithm for early detection of prediabetes and undiagnosed type 2 diabetes cases. Plans are also underway to expand the programme to other populations and languages. The Colive Voice study is a multilingual and inclusive program, exploring vocal biomarkers for diagnosing various chronic conditions.

The report concluded: “This work demonstrates the potential of using voice analysis in a diabetes context. A voice recording could potentially be soon used as a scalable, non-invasive first-line diabetes screening strategy. Future research should focus on targeting individuals with early-stage type 2 diabetes and prediabetes and expanding our findings to other populations in prospective studies. Given the high societal costs of undiagnosed diabetes in the USA, our findings open new perspectives to improve secondary prevention, reduce the impact of diabetes and prevent severe complications and premature diabetes-related mortality.”

Read the report in PLOS Digital Health

Read more about type 2 diabetes