The diagnoses made by the artificial intelligence They continue to make their way in the world of medicine. A recent study found a way for a machine learning mechanism to detect type 2 diabetes, with a simple voice message from a patient, lasting about 10 seconds, according to a note from D.W..
The world of science is surprised, since AI can detect type 2 diabetes with an accuracy of 89% in women and 86% in men, from the voice message. The research was carried out by a team of scientists from Stanford University and published in the journal Mayo Clinic Proceedings: Digital Health.
The research used a machine learning model to analyze participants’ voice patterns. The researchers found that patients with type 2 diabetes had significant differences in the pitch, intensity, and duration of their voice.
The scientists in charge of the research say that for the analysis of patients it is only enough to listen to telephone recordings.
They focus on issues such as: the melody of speech, the tones and the pauses they make while having a conversation.
The artificial intelligence was trained so that its algorithms can detect up to 200,000 different characteristics in the voice of humans. According to their patterns, they could find different different clinical pictures. They are working to optimize the detection of other diseases.
This discovery has the potential to revolutionize the diagnosis of type 2 diabetes. Diabetes is a chronic disease that affects millions of people around the world. Early diagnosis and treatment are essential to control the disease and prevent serious complications.