Idea density in Japanese for the early detection of dementia based on narrative speech.

Daisaku Shibata,Ayae Kinoshita,Hiroyuki Nagai,Taro Okahisa,Eiji Aramaki,Kaoru Ito,Hiroyoshi Ariga

doi:10.1371/journal.pone.0208418

Daisaku Shibata, Ayae Kinoshita + Show 5 more

Open Access

https://doi.org/10.1371/journal.pone.0208418

Copy DOI

Abstract

BackgroundIdea density (ID), a natural language processing–based index, was developed to aid in the detection of dementia through the analysis of English narratives. However, it has not been applied to non-English languages due to the difficulties in translating grammatical concepts. In this study, we defined rules to count ideas in Japanese narratives based on a previous study and proposed a novel method to estimate ID in Japanese text using machine translation.MaterialsThe study participants comprised 42 Japanese patients with dementia aged 69–98 years (mean: 84.95 years). We collected free narratives from the participants to build a speech corpus. The narratives of the patients were translated into English using three machine translation systems: Google Translate, Bing Translator, and Excite Translator. The ID in the translated text was then calculated using the Dependency-based Propositional ID (DEPID), an English ID scoring tool.ResultsThe maximum correlation coefficient between ID calculated using DEPID-R-ADD (a modified DEPID method to calculate ID after removing vague sentences) and the Mini-Mental State Examination score was 0.473, indicating a moderate correlation.DiscussionThe results demonstrate the feasibility of machine translation-based ID measurement. We believe that the basic concept of this translation approach can be applied to other non-English languages.

Highlights

The steady increase in life expectancy has led to severe health and sociological problems
The results showed that the highest correlation coefficient with the count by human raters was the Dependency-based Propositional ID (DEPID) count using Google Translate (r = 0.983), whereas the slope of the line yielded by DEPID using Bing Translator was the closest to 1 (α = 0.913)
We proposed a method for estimating Idea density (ID) in Japanese narratives using machine translation and automatic idea counting

Summary

Background

Idea density (ID), a natural language processing–based index, was developed to aid in the detection of dementia through the analysis of English narratives. It has not been applied to non-English languages due to the difficulties in translating grammatical concepts. We defined rules to count ideas in Japanese narratives based on a previous study and proposed a novel method to estimate ID in Japanese text using machine translation. The study participants comprised 42 Japanese patients with dementia aged 69–98 years (mean: 84.95 years). We collected free narratives from the participants to build a speech corpus. The narratives of the patients were translated into English using three machine translation systems: Google Translate, Bing Translator, and Excite Translator. The ID in the translated text was calculated using the Dependency-based Propositional ID (DEPID), an English ID scoring tool

Discussion

Introduction

Methods

Method Google Bing Excite

Method Google

Conclusion