How you carry yourself in the world, tells a whole lot about you. Our body is always giving out subtle and not-so-subtle signals about a whole assortment of things. For example, scientists have found that the way you walk could predict when you're going to die. Even the way you clench your fist or cross your arms can reveal a lot about you.
Discover our latest podcast
Of course, you express your personhood and likes and dislikes through talking, but surprisingly, how you talk can also give out cues about your health!
As per findings from a study funded by Klick Labs, and published in Mayo Clinic Proceedings: Digital Health, the way you speak can actually reveal if you have Type 2 Diabetes.
How speaking can reveal Type 2 Diabetes
it is important to note that Klick Labs is a company working on AI voice, and hence, has vested interest in the research they have funded. Klick Labs's products benefits from the findings of the research.
As per the research, significant differences were found between voice recordings of nondiabetic and Type 2 diabetic men and women. The findings could change how the medical community screens for this disease.
For the study, researchers asked 267 people (diagnosed as either non- or Type 2 diabetic) to record a phrase into their smartphone 6 times daily for a period of two weeks. These resulted in more than 18,000 recordings.
Studying these, scientists analysed for differences between non-diabetic and Type 2 diabetic individuals in 14 acoustic features. Researchers looked at factors such as pitch and intensity that can't be detected by human ear.
Voice technology and detection of Type 2 Diabetes
Jaycee Kaufman, first author of the paper and research scientist at Klick Labs, explains that voice technology can play a big role in screening Type 2 Diabetes, as
Current methods of detection can require a lot of time, travel, and cost. Voice technology has the potential to remove these barriers entirely.
This approach to screening is both non-intrusive as well as accessible, and could provide a potential new tool to doctors. The current diagnostic tools for prediabetes and Type 2 diabetes include the glycated hemoglobin (A1C), the fasting blood glucose (FBG) test and the OGTT.
To add to this, Klick Health proposes that just 10 seconds of voice recording could enable AI to spot Type 2 diabetes.
As per Yan Fossat, vice president of Klick Labs, the next steps for the company will be to replicate the study and expand their research using voice as a diagnostic in other areas such as prediabetes, women’s health and hypertension.
Read more:
⋙ The way you smell can let people know if you're single or coupled up
⋙ Do you talk to yourself? Here's when to worry
⋙ Man ruptures eardrums after passionate kissing: Here's the medical reason why
Sources used:
Klick Health: 'AI and 10 seconds of voice can screen for diabetes, new study in Mayo Clinic journal reveals'
Mayo Clinic Proceedings: Digital Health: ' Acoustic Analysis and Prediction of Type 2 Diabetes Mellitus Using Smartphone-Recorded Voice Segments'
