HomeAI News
AI diagnoses type 2 diabetes in 10 seconds using sound with 89% accuracy
21

AI diagnoses type 2 diabetes in 10 seconds using sound with 89% accuracy

Hayo News
Hayo News
November 2nd, 2023
View OriginalTranslated by Google

Canadian medical researchers trained a machine learning-based AI to identify 14 vocal differences between people with type 2 diabetes and those without diabetes. These characteristics include pitch, intensity, and other subtle changes in sound that are indistinguishable to the human ear. Type 2 diabetes is then diagnosed by listening to the patient's voice for 6 to 10 seconds.

Main principles

1. Sound signature recognition: AI models are trained to identify voice signatures associated with type 2 diabetes. These characteristics include pitch, intensity, and other subtle changes in sound that are indistinguishable to the human ear.

2. Machine learning training: Canadian medical researchers used 267 voice recordings from Indian residents to train AI. Of these, approximately 72% of participants were diagnosed as non-diabetic and the remainder were diagnosed with type 2 diabetes. All participants recorded a phrase six times a day for two weeks, resulting in a total of 18,000 recordings.

3. Voice difference analysis: Scientists identified 14 voice differences between people with type 2 diabetes and those without diabetes. Among them, four differences help AI diagnose type 2 diabetes more accurately.

4. Combine with other health data: In addition to voice data, AI also combines basic health data collected by researchers, such as age, gender, height and weight, to improve the accuracy of diagnosis.

Prediction effect

1. Diagnostic accuracy: AI can accurately diagnose type 2 diabetes in 89% of women and 86% of men. The study found that pitch and the standard deviation of pitch were useful features for diagnosing diabetes in all participants.

2. Gender differences: For women, the predictive features are average pitch, pitch SD and RAP jitter. For men, average intensity and apq11 shimmer were used. Briefly, these characteristic changes indicate that women with type 2 diabetes report slightly lower pitch and less variability, whereas men with type 2 diabetes report slightly weaker pitch and greater variability.

3. Potential applications: The researchers believe that sound analysis shows potential as a pre-screening or monitoring tool for type 2 diabetes, especially when combined with other risk factors associated with the condition.

Reprinted from View Original

Comments

no dataCoffee time! Feel free to comment