AI Can Soon Diagnose Patients Using Voice Notes
The US National Institute of Health has collaborated with the University of South Florida (USF), Cornell, and 10 other institutes and is collecting voice data to build an AI application that can diagnose diseases by analysing speech. It’s part of the Bridge2AI programme launched by the NIH (National Institute of Health) in 2020 with a fund of over $100 million.
From volume, pace, and intonation to vocal cord vibrations that human ears can’t hear, the AI application will examine even the minimal differences in voice. This app will even track down breathing patterns and help diagnose speech disorders, neurological diseases, mental health issues, respiratory problems, etc.
The study lead and director of the USF Health Voice Centre, Yael Bensoussan, shared, “Voice has the potential to be a biomarker for several health conditions. Creating an effective framework that incorporates huge datasets using the best of today’s technology in a collaborative manner will revolutionise the way voice is used as a tool for helping clinicians with diseases and disorders.”
Maria Espinola, a psychologist and assistant professor at the University of Cincinnati College of Medicine, talked about the role of voice in detecting health conditions. She revealed, “The speech of those with depression is generally more monotone, flatter and softer. They also have reduced pitch range and lower volume. They take more pauses. They stop more often.”
The Mayo Clinic published a study that used an Indian cohort to identify type 2 diabetes with more than 80% accuracy. All it took was listening to a 10-second voice sample. That study was a great success and utilised phone conversations with basic data like age, BMI, and gender to create a diagnosis.
What Disease Can The AI App Identify From Voice Clips?
There are a number of diseases that the AI app can identify from voice clips. Some of them are type 2 diabetes, Parkinson’s, Alzheimer’s, stroke, depression, schizophrenia, bipolar disorder, Heart failure, etc.
Although the program is revolutionary, there are some data privacy concerns for voice. It’s because voice can be identified easily compared to other health data of a patient. There is also a requirement for a wide variety of voices to work well with all patients across the world, Grace Change shared. Change founded Kintsugi which is developing technology for telehealth and call centre providers to identify patients needing further support.
