A study being presented at the European Association for the Study of Diabetes (EASD) annual meeting in Milan, Italy, running Sept. 28–Oct. 2, suggests that changes in a person's voice could be used to detect type 2 diabetes risk, according to Medical Xpress.
The research reportedly used an AI-based tool that analyzed just a few seconds of speech to identify signs of the condition, per Medical Xpress and the Daily Mail.
The Telegraph and Daily Mail both reported that the AI tool could detect diabetes from voice recordings or speech patterns, framing it as a potential new screening method. The Mirror similarly described the finding as a subtle voice change that could reveal diabetes risk.
Details on how the AI tool works, the size of the study, or its accuracy were not specified in the available reporting.
How each side covered it
Left
- The Mirror highlighted a subtle voice change as a potential indicator of type 2 diabetes risk detectable by a new AI programme.
“Subtle change to your voice could reveal your risk to new AI programme” — The Mirror
Center
- Medical Xpress reported the tool could detect signs of type 2 diabetes from just 20 seconds of speech.
- The findings were tied to research being presented at the EASD annual meeting in Milan, Sept. 28–Oct. 2.
“Just 20 seconds of speech could help detect type 2 diabetes using AI-based tool” — Medical Xpress
Right
- The Telegraph reported that AI could detect diabetes from voice recordings.
- Daily Mail described a test that could screen for type 2 diabetes in seconds using speech.
“A tool that uses artificial intelligence to scan for changes in speech could be used to diagnose type 2 diabetes in just seconds, a new study has found.” — Daily Mail
Questions readers ask
What did the new study find about type 2 diabetes and voice?
Researchers presenting at the European Association for the Study of Diabetes annual meeting in Milan reported that an AI-based tool could detect signs of type 2 diabetes from a short speech sample, according to Medical Xpress.
How much speech is needed for the AI tool to work?
According to Medical Xpress, just 20 seconds of speech could be enough for the AI tool to help detect type 2 diabetes.
Where and when was this research presented?
The research was presented at the EASD annual meeting in Milan, Italy, held Sept. 28 to Oct. 2, per Medical Xpress.
How did coverage differ across outlets?
Center outlet Medical Xpress focused on the specific detail that just 20 seconds of speech could be analyzed, while left-leaning and right-leaning outlets emphasized subtle voice changes and the AI tool's potential as a screening test.
Sources · 4 outlet reports
- The MirrorLeft-leaningType 2 diabetes symptoms: Subtle change to your voice could reveal your risk to new AI programme
- Medical XpressCenterJust 20 seconds of speech could help detect type 2 diabetes using AI-based tool
- Daily MailRight-leaningNew test could screen for type 2 diabetes in seconds using just speech, study shows
- The TelegraphRight-leaningAI could detect diabetes from voice recordings