AI can detect Parkinson’s disease through speech patterns

Credit: Unsplash+

Introduction to Parkinson’s Disease and AI

Parkinson’s disease (PD) is a neurological disorder that causes speech-related issues among other symptoms.

Recently, researchers used artificial intelligence (AI) to analyze speech patterns in PD patients, discovering that these individuals used more verbs and fewer nouns and fillers.

This study was conducted by Professor Masahisa Katsuno and Dr. Katsunori Yokoi at Nagoya University Graduate School of Medicine, in partnership with Aichi Prefectural University and Toyohashi University of Technology.

The findings were published in the journal Parkinsonism & Related Disorders.

How AI Can Understand Language

The technology used in this study, known as natural language processing (NLP), is a type of AI.

It allows computers to understand and interpret large amounts of human language data by spotting patterns using statistical models.

The researchers used NLP to identify differences in the speech of PD patients, focusing on 37 different characteristics in texts generated from free-flowing conversations.

Findings of the Study

The NLP analysis showed that PD patients used fewer common nouns, proper nouns, and fillers in each sentence.

In contrast, they used more verbs and varied case particles (a significant feature of the Japanese language) per sentence.

To illustrate this, Yokoi gave an example of how a PD patient might describe their morning: “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.”

In contrast, a healthy individual might say: “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.”

Yokoi noted that while both accounts are similar in length, PD patients tend to speak in shorter sentences, leading to the increased use of verbs.

Healthy individuals, on the other hand, often use more fillers like ‘well’ or ‘umm’ to connect their sentences.

Implications for Early Detection

The most encouraging aspect of this research is its potential for early detection. The study was conducted on PD patients who hadn’t yet displayed the typical cognitive decline associated with the disease.

Katsuno, the lead researcher, said, “Our results suggest that even in the absence of cognitive decline, the conversations of patients with PD differed from those of healthy subjects.”

The team was able to identify PD patients with over 80% accuracy based on these conversational changes, suggesting the potential of using natural language processing for early PD diagnosis.

If you care about Parkinson’s disease, please read studies about Vitamin E that may help prevent Parkinson’s disease, and Vitamin D could benefit people with Parkinson’s disease.

For more information about brain health, please see recent studies about new way to treat Parkinson’s disease, and results showing COVID-19 may be linked to Parkinson’s disease.

The study was published in Parkinsonism & Related Disorders.

Copyright © 2023 Knowridge Science Report. All rights reserved.