Natural language processing could be a successful means of analysing speech changes in Parkinson’s disease patients, leading to a more effective diagnosis.
This is the conclusion of Japanese researchers who have used artificial intelligence (AI) to process natural language and speech characteristics in people with Parkinson’s disease.
They found that these patients spoke using more verbs and fewer nouns and fillers – even in the absence of cognitive decline – than healthy subjects.
The study was led by Professor Masahisa Katsuno and Dr Katsunori Yokoi of Nagoya University Graduate School of Medicine, in collaboration with Aichi Prefectural University and Toyohashi University of Technology.
The results have been published in the journal Parkinsonism and Related Disorders.
Natural language processing (NLP) technology is a branch of AI that focuses on enabling computers to understand and interpret large amounts of human language data using statistical models to identify patterns.
Given that people with Parkinson’s disease experience a variety of speech-related problems, including impaired diction production and language use, the group used NLP to analyse differences in patient articulation patterns based on 37 characteristics using texts made from free conversations.
The analysis revealed that patients with Parkinson’s disease used fewer common nouns, proper nouns, and fillers per sentence. On the other hand, they spoke using a higher percentage of verbs and variance for case particles – an important feature of the Japanese language – per sentence.
An AI study has found that people with Parkinson’s disease speak differently to healthy patients. Image credit: Reiko Matsushita
According to Dr Yokoi: “When I asked them to talk about their day in the morning, a Parkinson’s disease patient might say something like the following, for example, ‘I woke up at 4:50 am. I thought it was a bit early, but I got up. It took me about half an hour to go to the toilet, so I washed up and got dressed around 5.30 am. My husband cooked breakfast. I had breakfast after 6 am. Then I brushed my teeth and got ready to go out.’”
“Whereas someone from the healthy control group might say something like this, ‘Well, in the morning, I woke up at six o’clock, and got dressed, and, yeah, washed my face. Then, I fed my cat and dog. My daughter prepared a meal, but I told her I couldn’t eat, and I, umm, drank some water.’
“While these are examples that we created of conversations reflecting the characteristics of people with Parkinson’s disease and healthy people, what you should see is that the total length is similar. However, Parkinson’s disease patients speak shorter sentences than people in the control group, leading to more verbs in the machine learning analysis.
“The healthy control also uses more fillers, such as ‘well’ or, ‘umm’, to connect sentences.”
The most promising aspect of this research is that the team performed the experiment on patients who did not yet show the characteristic cognitive decline seen in Parkinson’s disease, which is estimated to affect more than 10 million worldwide.
Their findings offer a potential means of early detection to distinguish Parkinson disease patients.
Professor Katsuno, the head of the study, concluded: “Our results suggest that even in the absence of cognitive decline, the conversations of patients with Parkinson’s disease differed from those of healthy subjects.
“When we attempted to identify Parkinson’s disease patients or healthy controls based on these conversational changes, we could identify Parkinson’s disease patients with over 80% precision. This result suggests the possibility of language analysis using natural language processing to diagnose Parkinson’s disease.”
Parkinson’s is a life changing, progressive neurodegenerative condition affecting both men and women. But twice as many males as females are at risk of developing the disease, although women have a higher mortality rate and see faster progression of the condition.
The main symptoms are slowness of movement, stiff muscles and tremor. Speech and communication difficulties are also common symptoms of the progressive disease, for which there is currently no cure.
Parkinson’s usually affects those in the 60-plus age group, although younger people can get early-onset forms, most famously the Hollywood actor Michael J Fox, who was just 29 when he was diagnosed.