A collaboration between universities in Australia and Iraq has shone the light on a potential new early detection technique for Parkinson’s disease.
Researchers from Middle Technical University (MTU) in Baghdad and the University of South Australia (UniSA) studying artificial intelligence (AI) techniques to detect the disease, found algorithms could detect subtle changes in a person’s voice.
MTU Associate Professor Ali Al-Naji, a medical instrumentation engineer and UniSA adjunct, said this presented the possibility of creating a new diagnostic tool for Parkinson’s disease (PD).
Associate Professor Al-Naji said all the evidence showed that AI-powered voice analysis could revolutionise early PD diagnosis and remote monitoring of the neurodegenerative disorder.
He said speech impairments were often the first indicators of the fastest-growing neurological disease in the world, but traditional diagnostic methods were often complex and slow, delaying early detection.
“Vocal changes are early indicators of Parkinson’s disease, including small variations in pitch, articulation and rhythm, due to diminished control over vocal muscles.
“By analysing these acoustic features, AI models can detect subtle, disease-related vocal patterns long before visible symptoms appear.”
Associate Professor Al-Naji said AI techniques primarily used machine learning and deep learning algorithms trained on extensive data sets from simple voice recordings from Parkinson’s patients and healthy controls.
“These algorithms extract relevant features, such as pitch, speech distortions and changes in vowels, and then categorise the voice recordings with remarkable accuracy – as high as 99 percent.”
He said while Parkinson’s had no cure, early diagnosis and intervention could improve quality of life and slow the progression of symptoms.
Access the full paper: Parkinson’s disease detection from voice using artificial intelligence techniques: A review.
