Researchers involved in a recent study trained an artificial intelligence (AI) model to diagnose type 2 diabetes in patients after six to 10 seconds of listening to their voice. Canadian medical researchers trained the machine-learning AI to recognise 14 vocal differences in the voice of someone with type 2 diabetes compared to someone without diabetes. […]
The auditory features that the AI focussed on included slight changes in pitch and intensity, which human ears cannot distinguish. This was then paired with basic health data gathered by the researchers, such as age, sex, height and weight.
When this was posted a few weeks ago, it was also pointed out that your socioeconomic status and geographical location can probably also be predicted pretty well by voice, which also correlate with T2D risk factors.
It is a neat finding and all, but unless there is some underlying physiological tie between T2D and your voice that’s not explainable otherwise, it’s kind of the diagnostic equivalent of “psychic” cold reading.
Not quite just voice but still impressive
I bet age, weight, and height were probably bigger factors than the voice. Also larger people probably have a lower voice.
Yeah there is really solid, large scale studies that associate diabetes incidence against sex, age, and BMI. Really tight CI on the data.
When this was posted a few weeks ago, it was also pointed out that your socioeconomic status and geographical location can probably also be predicted pretty well by voice, which also correlate with T2D risk factors.
It is a neat finding and all, but unless there is some underlying physiological tie between T2D and your voice that’s not explainable otherwise, it’s kind of the diagnostic equivalent of “psychic” cold reading.