AI and 10 seconds of voice can screen for diabetes, new study in Mayo Clinic journal reveals
AI and 10 seconds of voice can screen for diabetes, new study in Mayo Clinic journal reveals

Discover what everyone is saying about Klick Labs’ latest groundbreaking research.
Discover what everyone is saying about Klick Labs’ latest groundbreaking research.

Published in Mayo Clinic Proceedings: Digital Health, the study 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.
For the study, Klick Labs researchers asked 267 people (diagnosed as either non- or Type 2 diabetic) to record a phrase into their smartphone six times daily for two weeks. From more than 18,000 recordings, scientists analyzed 14 acoustic features for differences between non-diabetic and Type 2 diabetic individuals.
Here’s what news media around the world are saying:



This AI app will soon screen for type 2 diabetes using just a 6-10 second voice clip
Developed by Klick Health in Toronto, Canada, an AI engine helps power technology that can detect the disease based on the characteristics of your voice.
Diabetes screening may be as simple as speaking into smartphone with new AI app, researchers say
Getting screened for type 2 diabetes could one day be as simple as speaking into your smartphone.
Study: Your Voice May Reveal If You Have Type 2 Diabetes
The most common and accurate way to diagnose diabetes, including prediabetes and type 2, is through blood tests. However, a new study suggests that type 2 diabetes could also be detected in a person’s voice.
Klick’s latest health tech uses a person’s voice and artificial intelligence to detect diabetes
Can reading a single sentence lead to a type 2 diabetes diagnosis? It may be possible with a new Klick Labs prototype application.
AI and 10 seconds of voice recording can screen for diabetes, study suggests
Scientists used six to ten seconds of people’s voices, along with basic health data, including age, sex, height, and weight, to create an AI model.
How diabetes changes your voice, and why it could be very useful
Diabetes can affect just about every part of your body, from your toes to the very top of your head. A new study claims that it can change your voice, too.
Short voice recordings can be used to test people for diabetes, study finds
Previous research has found short voice recordings - in combination with AI - can diagnose other illnesses, including COVID-19.
Could a 10-second voice clip help diagnose diabetes?
Currently, the most common and accurate methods for diagnosing type 2 diabetes involve blood work. A new study, however, asserts that type 2 diabetes can now be diagnosed based on the sound of a person’s voice.
AI can detect diabetes — just by listening to you talk for 10 seconds: new study
Talk to your robo-doctor. New medical research finds that artificial intelligence can detect type 2 diabetes merely by listening to a patient speak for six to ten seconds.
These Toronto researchers found a way to detect Type 2 diabetes using a 10-second voice test
The new, AI-powered model accurately predicted the disease in over 85 percent of patients using a six to ten second voice clip, new study finds.
10 Seconds Of Recorded Speech Can Reveal If Someone Has Diabetes
If you’ve avoided being tested because you’re scared of needles, help may be at hand.
New AI Tool Can Diagnose Type 2 Diabetes in Seconds by Listening to Your Voice
This groundbreaking tech is a potential game changer in Type 2 diabetes detection.
AI can diagnose people with diabetes in 10 SECONDS using voice recording, new study reveals
Canadian medical researchers have trained a machine-learning AI to accurately predict Type 2 diabetes from just six to 10 seconds of the patient's spoken voice.
Klick Labs develops AI model to screen for type 2 diabetes using voice audio
Klick Labs has developed an artificial intelligence (AI) model that is capable of determining whether a person has type 2 diabetes using six to 10 seconds of voice audio.
Short voice recordings can be used to test people for diabetes, study finds
People could be diagnosed with diabetes using little more than a short voice recording from their phone, according to a new study.
IA escuta 10 segundos da sua voz e "diagnostica" diabetes tipo 2
Já imaginou mandar um áudio de 10 segundos falando e receber um possível diagnóstico de diabetes tipo 2, sugerido por uma ferramenta com Inteligência Artificial (IA)? É o que propõem os cientistas do Klick Labs, no Canadá, numa missão que envolve usar a tecnologia de voz em prol da saúde.
The Agenda with Georgia Tolley
Starts at 23:50 - “This is one of those clear examples of how AI has been used to cut down research time...Completely fascinating.”
IA: De Courts Enregistrements Vocaux Peuvent Déceler Des Maladies Comme Le Diabète
Une étude a démontré la possibilité de diagnostiquer des maladies à partir d'un court enregistrement vocal. Cette technique, basée sur l'intelligence artificielle, peut notamment identifier des diabétiques.
Una IA detecta en 10 segundos si tienes diabetes. Solo tienes que hablar
Junto a datos básicos de salud, el modelo de inteligencia artificial puede distinguir si ese individuo tiene diabetes tipo 2 o no.
AI chẩn đoán bệnh tiểu đường qua giọng nói trong 10 giây
Chỉ cần nói vài câu vào điện thoại thông minh, mọi người có thể biết mình mắc bệnh tiểu đường hay không.
About Klick Applied Sciences (including Klick Labs)
Klick Applied Sciences’ diverse team of data scientists, engineers, and biological scientists conducts scientific research and develops AI/ML and software solutions as part of the company’s work to support commercial efforts using its proven business, scientific, medical, and technological expertise. Its 2019 Voice Assistants Medical Name Comprehension study laid the scientific foundation for rigorously testing voice assistant consumer devices in a controlled manner.