2023-05-12 13:38:57
Using artificial intelligence (AI) to process natural language, a group of researchers from the School of Medicine of the Nagoya University (Japan) has evaluated speech characteristics among patients with Parkinson’s disease (PD). AI analysis of their data determined that these patients spoke differently from healthy people. The study led by Masahisa Katsuno and Katsunori Yokoi has been published in the journal «Parkinsonism & Related Disorders».
the technology of natural language processing (PLN) is a branch of AI that focuses on training computers to understand and interpret large amounts of human language data using statistical models to identify patterns. Since PD patients experience a variety of speech-related problems, including impaired speech production and language use, the group used NLP to analyze differences in the patients’ speech patterns based on 37 features using texts made from free conversations.
The analysis revealed that PD patients used fewer common, proper, and filler nouns per sentence. On the other hand, they spoke using a higher percentage of verbs and case particle variance (an important feature of the Japanese language) per sentence.
According to Yokoi, “When asked to talk about their day in the morning, a PD patient might say something like the following, for example: ‘I woke up at 4:50 in the morning. It seemed a little early, but I got up. It took me half an hour to go to the bathroom, so I washed and dressed around 5:30 in the morning. My husband prepared breakfast. I had breakfast after 6 in the morning. Then I brushed my teeth and got ready to go out.”
Yokoi adds, “Whereas someone in the healthy control group might say something like, ‘Well, in the morning, I woke up at six, got dressed and, yeah, washed my face. Then I fed my cat and my dog. My daughter made a meal, but I told her she couldn’t eat, and I, umm, drank some water.”
“Although these are examples we created of conversations that reflect the characteristics of people with PD and healthy people, the thing to look at is that the overall length is similar,” Yokoi explained. “However, PD patients speak shorter sentences than people in the control group, resulting in more verbs in the machine learning analysis. The healthy control group also used more filler words, like ‘nice’ or ‘umm’, to connect sentences.”
This result suggests the possibility of language analysis using natural language processing to diagnose PD.
The most promising aspect of this research is that the team conducted the experiment on patients who did not yet show the characteristic cognitive decline of PD. Therefore, their findings offer a potential means of early detection to distinguish patients with PD.
“Our results suggest that, even in the absence of cognitive impairment, the conversations of PD patients differed from those of healthy subjects,” concludes Professor Katsuno, who led the study. “When we tried to identify PD patients or healthy controls based on these conversational changes, we were able to identify PD patients with greater than 80% accuracy. This result suggests the possibility of language analysis using natural language processing to diagnose PD.”
#Parkinsons #patients #speak #differently #healthy