Canadian health researchers have trained artificial intelligence (AI) to accurately diagnose type 2 diabetes in just 6 to 10 seconds, using the patient’s voice.
According to the Daily Mail, a research team at Klick Labs (USA) achieved this milestone after their AI machine learning model identified 14 distinct sound features between healthy individuals and those with type 2 diabetes.
AI will provide more accurate diagnoses when age and body mass index (BMI) of the patient are included in the prediction model. (Illustration: Shutterstock)
The AI focused on a set of voice characteristics, including subtle changes in pitch and intensity that are inaudible to the human ear. This data was then combined with basic health information, including age, gender, height, and weight of the study participants.
Researchers found that gender plays a significant role: AI can diagnose the disease accurately at a rate of 89% for women, but slightly less accurately at 86% for men.
This AI model promises to significantly reduce the costs of medical consultations. The research team indicated that Klick Labs’ model will be more accurate with the inclusion of additional data on the patient’s age and body mass index (BMI).
Mr. Yan Fossat, Deputy Director of Klick Labs and the lead researcher on the model, is confident that their voice technology product has tremendous potential in identifying type 2 diabetes and other health conditions.
Professor Fossat also teaches at Ontario Tech University, specializing in mathematical modeling and computational science for digital health.
He hopes that Klick’s non-invasive and accessible AI diagnostic method could pave the way for disease diagnosis through a simple mobile application. This would help identify and assist millions of people with type 2 diabetes who may not have the opportunity to undergo screening.
He also expressed hopes to expand this new research into other medical fields, such as prediabetes, women’s health, and hypertension.
