Voice Technology and AI Combine to Detect Type 2 Diabetes, According to Klick Labs Study
A groundbreaking study conducted by Klick Labs has introduced a pioneering method that utilizes voice technology and artificial intelligence (AI) to detect Type 2 diabetes. By utilizing short voice recordings and basic health information, such as age, gender, height, and weight, researchers were able to train an AI model to accurately identify Type 2 diabetes. The model achieved an impressive 89 percent accuracy rate for women and 86 percent for men.
The lead author of the study, Jaycee Kaufman, emphasized the potential of this research in transforming diabetes screening. With traditional methods often requiring significant time, expense, and travel, the integration of voice technology could eliminate these barriers entirely.
During the study, 267 participants, classified as non-diabetic or Type 2 diabetic, were instructed to record a specific phrase on their smartphones six times daily for two weeks. With over 18,000 audio recordings, researchers meticulously analyzed 14 acoustic features to distinguish between non-diabetic and Type 2 diabetic individuals.
The research focused on various vocal attributes, including imperceptible alterations in pitch and intensity. Signal processing techniques were employed to capture voice changes associated with Type 2 diabetes, and it was found that these variations manifested differently in males and females.
Globally, approximately 90 percent of diabetes cases are Type 2 diabetes, with nearly half of the 240 million adults with diabetes being unaware of their condition, according to the International Diabetes Federation. Current diagnostic tests for prediabetes and Type 2 diabetes require visits to healthcare providers and examinations such as the glycated hemoglobin (A1C) test, fasting blood glucose (FBG) test, and the oral glucose tolerance test (OGTT).
Klick Labs’ non-invasive approach to detecting Type 2 diabetes offers a more accessible and affordable digital screening tool. Yan Fossat, Vice President of Klick Labs and principal investigator of the study, highlighted the potential of this approach to screen large populations and identify undiagnosed cases. Fossat also outlined future steps, including further research into voice-based diagnostics for prediabetes, women’s health, and hypertension.
This groundbreaking discovery builds upon Klick Labs’ extensive expertise and investment in machine learning, data science, and AI, particularly within the field of diabetes research. Their previous study, “Homeostasis as a proportional-integral control system,” published in Nature Digital Medicine in 2020, explored mathematical modeling to determine changes in glucose regulation. The latest study by Klick Labs was published in Mayo Clinic Proceedings: Digital Health.
With the potential to revolutionize healthcare practices, voice technology and AI offer a promising solution for detecting Type 2 diabetes and other health conditions. Klick Labs’ research underscores the importance of accessible and affordable digital screening tools in improving healthcare outcomes.
Source: Klick Labs via Tech Times
Image: FRANCE-HEALTH-VIRUS-DIABETES (FRANCK FIFE/AFP via Getty Images)
I have over 10 years of experience in the cryptocurrency industry and I have been on the list of the top authors on LinkedIn for the past 5 years. I have a wealth of knowledge to share with my readers, and my goal is to help them navigate the ever-changing world of cryptocurrencies.