Summary: Researchers have identified disease-specific reductions in emotional expressivity in dementia with Lewy bodies through extensive neural network analysis.
This reduced vocal expression is linked to cognitive impairment and atrophy of brain regions, which distinguishes it from Alzheimer’s disease. Their study suggests that analyzing vocal emotions could facilitate early detection and appropriate care.
Highlights:
- Lewy body dementia presents with distinct reductions in vocal emotional expressivity.
- This reduction is associated with cognitive impairment and atrophy of the insular cortex.
- Deep neural network techniques can differentiate Lewy body dementia from other dementias.
Source: University of Tsukuba
Researchers from the University of Tsukuba and IBM Research have identified, for the first time, a specific reduction in emotional expressivity in dementia with Lewy bodies by quantifying vocal expression of emotions using techniques deep neural networks.
This reduction in vocal emotional expressions was associated with cognitive impairment and brain region-specific atrophy and may serve as a distinguishing factor for people with dementia with Lewy bodies.
Lewy body dementia is the second most common neurodegenerative dementia after Alzheimer’s disease. It progresses more quickly and has a wider range of symptoms than other forms of dementia, significantly decreasing patients’ quality of life.
However, due to the overlap of symptoms with other diseases such as Alzheimer’s disease and the limited availability of specialized doctors and facilities, dementia with Lewy bodies often remains undiagnosed.
Decreased emotional expression, a typical symptom in dementia patients, affects quality of life, for example by impairing daily communication and negatively impacting mental health. Despite its importance, no studies have objectively and quantitatively investigated emotional expression in people with dementia with Lewy bodies.
In their new study published in Alzheimer’s and dementia: diagnosis, assessment and monitoring of the disease, researchers collected voice data during story reading from people with Lewy body dementia and Alzheimer’s disease and compared it to data from cognitively unimpaired older adults (group witness). Vocal emotional expression was quantitatively compared using a deep learning-based emotion recognition model.
Results revealed that the Lewy body dementia group had more negative and calmer emotional expressions and lower overall expressiveness than the Alzheimer’s disease and control groups. This reduction was associated with cognitive impairment and atrophy of the insular cortex, both typical in people with dementia with Lewy bodies.
Furthermore, automated analysis of vocal emotional expressions demonstrated the potential of vocal emotional expression to differentiate individuals with dementia with Lewy bodies from other groups.
Researchers believe that using deep neural networks to analyze vocal emotional expression can potentially facilitate early detection and provision of appropriate care for dementia with Lewy bodies.
About this research news on AI and dementia
Author: Masatomo Kobayashi
Source: University of Tsukuba
Contact: Masatomo Kobayashi – University of Tsukuba
Picture: Image is credited to Neuroscience News
Original research: Free access.
“Vocal expression of emotions distinguishes Lewy body dementia from Alzheimer’s disease” by Masatomo Kobayashi et al. Alzheimer’s and dementia: diagnosis, assessment and monitoring of the disease
Abstract
Vocal expression of emotions distinguishes Lewy body dementia from Alzheimer’s disease
Dementia with Lewy bodies (DLB) and Alzheimer’s disease (AD), the two most common neurodegenerative dementias, both exhibit impaired emotional processing. However, how vocal emotional expressions change and differ between DLB and AD remains unexamined.
We collected vocal data during story reading from 152 older adults comprising DLB, AD, and cognitively intact (CU) groups and compared their emotional prosody in terms of valence and arousal dimensions.
Compared to matched AD and CU participants, DLB patients showed reduced overall emotional expressivity, as well as lower valence (more negative) and lower arousal (calmer), the extent of which was associated with cognitive impairment and insular atrophy. Classification models using voice features discriminated DLB from AD and CU with an AUC of 0.83 and 0.78, respectively.
Our results may help distinguish DLB patients from AD and UC individuals, serving as a surrogate marker for clinical and neuropathological changes in DLB.
News Source : neurosciencenews.com
Gn Health
