Parkinson’s disease is a neurodegenerative disorder affecting millions of people’s movement and coordination worldwide. One of the common symptoms of Parkinson’s disease is speech impairment, which can make communication difficult and affect the quality of life of patients and their caregivers.
Researchers from Nagoya University and Tokyo Institute of Technology have developed a novel method to analyze speech patterns in Parkinson’s disease patients using artificial intelligence (AI). They used a deep neural network, a machine learning algorithm, to extract features from speech samples of 50 people with Parkinson’s disease and 50 healthy controls. They then trained another neural network to classify the speech samples based on these features.
The results, published in Scientific Reports, showed that the AI method could reveal distinct speech patterns in Parkinson’s disease patients that were not detectable by human ears. These speech patterns were related to changes in pitch, loudness, voice quality, and articulation. The researchers also found that these speech patterns were correlated with the severity of motor symptoms and cognitive impairment in Parkinson’s disease patients.
The AI method identified Parkinson’s disease patients with over 80% accuracy, suggesting a potential for early diagnosis and monitoring of the disease progression. The researchers hope that their method can be applied to other languages and speech disorders, and contribute to the development of new therapies and assistive technologies for people with speech impairments.
Leave a Reply