RESEARCHERS from Iraq and Australia have partnered to publish a conference paper outlining how AI can help to diagnose Parkinson's Disease.
Key to the study is curating AI algorithms to detect subtle changes to a person's voice, often one of the first indicators of one of the world's fastest growing neurological diseases.
The academics from Middle Technical University (MTU) in Baghdad and the University of South Australia say evidence shows AI-powered voice analysis could revolutionise early Parkinson's diagnosis and remote monitoring.
"Vocal changes are early indicators of Parkinson's disease, including small variations in pitch, articulation and rhythm, due to diminished control over vocal muscles," said MTU Associate Professor Ali Al-Naji.
Algorithms are being trained to extract features such as pitch, speech distortions and vowel changes to categorise voice recordings, with some studies returning accuracy scores as high as 99%.
The above article was sent to subscribers in Pharmacy Daily's issue from 22 Nov 24
To see the full newsletter, see the embedded issue below or CLICK HERE to download Pharmacy Daily from 22 Nov 24
