Researchers from Nagoya University Graduate School of Medicine, Aichi Prefectural University and Toyohashi University of Technology have used natural language processing (NLP), a subfield of artificial intelligence (AI), to analyze the characteristics of speech among patients with Parkinson’s disease (PD). The study aimed to investigate the differences in speech patterns between patients with PD and healthy individuals, using statistical models to identify patterns.
The analysis showed that PD patients used fewer common nouns, proper nouns, and fillers, but they spoke using a higher percentage of verbs and variance for case particles per sentence. The team created examples of conversations reflecting the characteristics of people with PD and healthy individuals, and the total length of both conversations was similar. However, PD patients spoke shorter sentences, leading to more verbs in the machine learning analysis. Healthy individuals also used more fillers 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 PD, offering a potential means of early detection to distinguish PD patients. When they attempted to identify PD patients or healthy controls based on these conversational changes, they could identify PD patients with over 80% precision.
The study’s findings suggest the possibility of language analysis using natural language processing to diagnose PD, and even in the absence of cognitive decline, the conversations of patients with PD differed from those of healthy individuals.
Source : Nagoya University