Researchers from the University of Tsukuba have developed a mobile application that uses speech data to detect early signs of Alzheimer’s disease (AD) and mild cognitive impairment (MCI).
The prototype application, designed to be user-friendly and self-administered, addresses the growing need for screening tools that can be used in everyday life.
Tackling the Challenge of Speech Recognition in the Elderly
Language impairments often occur in the early stages of AD, and linguistic features characteristic of these impairments can be used for automatic detection of the disease.
However, automatic speech recognition tends to be less accurate for elderly individuals, posing a challenge to the development of an automatic tool.
To overcome this, the Tsukuba researchers collected and analyzed speech data from 114 participants, including AD patients, MCI patients, and cognitively normal participants.
The participants performed five cognitive tasks based on neuropsychological assessments used for dementia screening, including picture description and verbal fluency tasks.
Promising Results for Early Detection of Alzheimer’s and MCI
The results of the study showed that language impairments, particularly those related to semantic aspects like informativeness and vocabulary richness, could be reliably estimated even at poor speech recognition accuracy.
By combining these linguistic features with acoustic and prosodic features of the participant’s voice, machine learning models were able to detect MCI and AD with 88% and 91% accuracy, respectively.
These findings, published in the journal Computer Speech & Language, demonstrate the feasibility of an automatic, self-administered screening tool for detecting AD and MCI.
This is the first study to show such a tool can reliably capture language impairments from speech data obtained under poor automatic speech recognition accuracy conditions.
Future Implications
The proposed tool could significantly increase access to early detection of AD, allowing for interventions to begin at the MCI stage, potentially preventing or delaying the progression of the disease.
As this is a prototype, more research, and development will likely be required before the tool becomes widely available.
If you care about brain health, please read studies about vitamin D deficiency linked to Alzheimer’s and vascular dementia, and higher magnesium intake could help benefit brain health.
For more information about health, please see recent studies about how drinking milk affects risks of heart disease and cancer, and results showing strawberries could help prevent Alzheimer’s disease.
The study was published in Computer Speech & Language.
Copyright © 2023 Knowridge Science Report. All rights reserved.