It will be possible to find out if a person is diabetic by simply having them say a few sentences in a smartphone application. A revolutionary study has demonstrated that voice technology combined with artificial intelligence (AI) represents a major step forward in diabetes detection, News.ro announces.
The new study, published in Mayo Clinic Proceedings noted that AI and 10 seconds of voice could change the way people detect diabetes, providing better access and lower costs than current screening methods. Accuracy is 89% for women and 86% for men in predicting type 2 diabetes from acoustic vocal functions, according to Digital Health.
The researchers used six to 10 seconds of people’s voices, along with basic health data, including age, gender, height and weight, to create an AI model that can distinguish whether that person has type 2 diabetes.
Scientists asked 267 people (diagnosed as either non-diabetic or type 2 diabetic) to record a phrase on their smartphone six times a day for two weeks. From more than 18,000 recordings, the scientists analyzed 14 acoustic features for differences between non-diabetic and type 2 diabetic individuals.
“Our research highlights significant vocal variations between people with and without type 2 diabetes and could transform the way the medical community assesses diabetes. Current detection methods can be time-consuming, travel-intensive and costly. Voice technology has the potential to completely remove these barriers,” said Jaycee Kaufman, first author of the paper and researcher at Klick Labs.
The team at Klick Labs analyzed a number of vocal characteristics, such as changes in pitch and intensity that cannot be perceived by the human ear. Using signal processing, scientists were able to detect voice changes caused by type 2 diabetes.
“Surprisingly, those vocal changes manifested themselves in different ways for men and women,” Kaufman said, according to medicalxpress.com.
A potential new screening tool for undiagnosed diabetes
240 million adults worldwide living with diabetes do not know they have the condition, and nearly 90% of diabetes cases are type 2 diabetes, according to the International Diabetes Federation. The most commonly used diagnostic tests for prediabetes and type 2 diabetes include glycated hemoglobin (A1C), along with the fasting blood glucose (FBG) test and the OGTT—all of which involve a visit to a health care provider.
Yan Fossat, vice president of Klick Labs and principal investigator of this study, said that Klick’s non-intrusive and accessible approach offers the potential to screen large numbers of people and help identify the large percentage of undiagnosed people with type 2 diabetes. 2.
“Our research highlights the tremendous potential of voice technology in identifying type 2 diabetes and other health conditions. Voice technology could revolutionize health care practices as an affordable and accessible digital screening tool,” said Fossat who believes the next steps will be to replicate the study and expand their research using voice as a diagnosis in other areas such as prediabetes, health women and hypertension.
In Romania 1 out of 12 adults has diabetes, and in Europe 1 out of 11 adults. In addition, it is estimated that 1 out of 2 people does not know that they have diabetes, according to the data of the Diabetes Barometer in Romania.
“Romania has one of the highest rates of diabetes in Europe. It is a major public health problem, due to the ever increasing numbers, to which are added the estimates related to the large number of those who do not know that they are living with diabetes or who are in the prediabetes phase. The barometer made by the Romanian Diabetes Forum gives us a clear perspective, expressed in numbers, of the danger that diabetes represents in our country,” declared Prof. Univ. Dr. Gabriela Roman, President, Romanian Federation of Diabetes, Nutrition and Metabolic Diseases.
2023-10-20 20:08:18
#Diabetic #detection #voice #technology #artificial #intelligence #Accuracy #women #men #predicting #type #diabetes
