Recent studies show how linguistic analysis by researchers can spotlight early dementia through speech clues, paving the way for earlier diagnoses and better care.
Rapid Rise of Dementia
In Southeast Asia, the incidence of Alzheimer’s disease and other dementias is projected to soar, with new estimates suggesting that cases could rise to 10.5 million by 2050– a 238% increase from the 3.1 million cases recorded in 2019. This alarming rise on top of the ageing population is presenting significant strains and challenges in healthcare. Consequently, there is an urgent need for advancements in early diagnosis and intervention.
A recent breakthrough study conducted by researchers at the National University of Singapore (NUS) offers promising insights into early detection through language and speech analysis.
The study was published in the journal Alzheimer’s & Dementia: Diagnosis, Assessment and Disease Monitoring on 18 April 2024.
This article delves into the findings of this Singapore-based research and examines additional evidence from other studies to illustrate the potential of language analysis to shift the dementia diagnosis paradigm.
Read also: Dementia in Singapore Drops to 1 in 11 Older Adults
Key Findings from the Singapore Study
The study leveraged computational linguistics to analyse the natural speech patterns of elderly Singaporeans, revealing linguistic markers that could aid in early dementia detection.
The pivotal findings are as follows:
- Natural Speech Analysis: Automated speech analysis tools were employed to examine over 267,310 words from participants’ conversations. These tools identified significant differences in speech patterns between cognitively healthy individuals and those with mild cognitive impairment (MCI), particularly in the usage and complexity of nouns.
- Differences in Noun Usage: The research distinguished between amnestic MCI, which primarily affects memory, and non-amnestic MCI, as well as healthy controls. It found that individuals with amnestic MCI used fewer and more abstract nouns compared to those with non-amnestic MCI and healthy individuals. An abstract noun refers to a concept, idea, or quality that cannot be physically sensed, such as happiness, bravery, or justice.
- Imageability Problem: The findings indicate that individuals with amnestic MCI exhibit a significant imageability problem. This issue manifests as a diminished ability to evoke mental images through typically concrete words, which are usually associated with strong mental imagery. Interestingly, this impairment does not extend to their use of verbs, which appear unaffected.
- Implications for Early Detection: The ability to detect subtle changes in speech could enable healthcare professionals to diagnose and intervene at an earlier stage of cognitive decline, potentially slowing the progression of dementia.
Comments from Study Researchers
The study’s principal investigator, NUS Department of ELTS Professor Bao Zhiming, shared. “Previous studies had analysed targeted and smaller volumes of language data through word-based fluency tests, structured interviews and picture narrations. Our study has never been done before as it focused on unstructured and spontaneous speech that is easy to collect and analyse.”
He noted that Singapore provides a unique environment for this research as there is a wide variety of language used in this country, with four official languages and a blend of various dialects.
“The study of natural speech to detect linguistic signs of early cognitive decline is a reliable, non-invasive and cost-effective tool that could possibly help medical practitioners in the early diagnosis, intervention and management of the progressive disease.” shared Dr Luwen Cao, also from the NUS Department of ELTS.
This research not only highlights the utility of speech analysis in identifying early signs of dementia but also opens new avenues for non-invasive, cost-effective screening methods that could be integrated into regular healthcare settings.
How Linguistic Research is Transforming Early Dementia Diagnosis
These recent advancements in linguistic research are transforming the way we detect and diagnose dementia.Several other studies have demonstrated the efficacy of language analysis in identifying early signs of cognitive decline, paving the way for earlier interventions and better patient outcomes.
Here is a closer look at these significant findings:
- Machine Learning and Alzheimer’s Diagnosis: Research utilising the DementiaBank corpus achieved over 81% accuracy in identifying Alzheimer’s disease from narrative speech samples. This study pinpointed specific linguistic impairments—semantic, syntactic, and informational—that are characteristic of Alzheimer’s, showcasing the effectiveness of computational techniques.
- Challenges in Spoken Word Recognition: A study demonstrated that individuals with mild dementia symptoms struggle significantly with spoken word recognition, both in quiet and noisy settings. This finding indicates how dementia affects speech perception and cognitive processing.
- Sentence Repetition as a Diagnostic Tool: Analysis of sentence repetition tasks among native Greek speakers revealed that changes in syntax and grammar are early indicators of cognitive decline. This suggests that linguistic tests, which are non-invasive, could play a crucial role in the early diagnosis of Alzheimer’s disease.
- Role of Figurative Language in Early Detection: A comprehensive review indicated that impairments in figurative language might serve as early markers of cognitive decline, varying by the type and stage of dementia. Incorporating tests that assess these language skills could improve the sensitivity of early diagnostic protocols.
Together, these studies suggest the potential value of integrating linguistic assessments into diagnostic processes, enabling earlier and more accurate identification of dementia.
Conclusion
The recent surge in linguistic research highlights its critical role in the early diagnosis of dementia, in that subtle changes in language could be early indicators of cognitive decline. Healthcare professionals should be vigilant in monitoring these changes in their patients and advise family members to watch for alterations in speech patterns. This includes reduced word recall, increased use of abstract nouns, or difficulties with word identification.
By recognising these early signs, medical practitioners can initiate timely interventions that may slow the progression of dementia and significantly improve patient outcomes.
References
- Russell, G. (2022, May 25). Southeast Asia braces for rising dementia caseload. Asia Financial. https://www.asiafinancial.com/southeast-asia-braces-for-rising-dementia-caseload
- Cao, L., Han, K., Lin, L., Hing, J., Ooi, V., Huang, N., Yu, J., Ng, T. K. S., Feng, L., Mahendran, R., Kua, E. H., & Bao, Z. (2024, April 18). Reversal of the concreteness effect can be detected in the natural speech of older adults with amnestic, but not non-amnestic, mild cognitive impairment. Alzheimer’s Association. https://doi.org/10.1002/dad2.12588
- Fraser, K. C., Meltzer, J. A., & Rudzicz, F. (2016). Linguistic features identify Alzheimer’s disease in narrative speech. Journal of Alzheimer’s Disease, 49(2), 407-422. https://doi.org/10.3233/JAD-150520
- McClannahan, K. S., Mainardi, A., Luor, A., Chiu, Y. F., Sommers, M. S., & Peelle, J. E. (2022). Spoken word recognition in listeners with mild dementia symptoms. Journal of Alzheimer’s Disease, 90(2), 749-759. https://doi.org/10.3233/JAD-215606
- Kaltsa, M., Tsolaki, A., Lazarou, I., Mittas, I., Papageorgiou, M., Papadopoulou, D., Tsimpli, I. M., & Tsolaki, M. (2024, July 31). Language markers of dementia and their role in early diagnosis of Alzheimer’s disease: Exploring grammatical and syntactic competence via sentence repetition. Journal of Alzheimer’s Disease Reports, 8(1), 1115-1132. https://doi.org/10.3233/ADR-230204
- Chakrabarty, M., Klooster, N., Biswas, A., & Chatterjee, A. (2023, October). The scope of using pragmatic language tests for early detection of dementia: A systematic review of investigations using figurative language. Alzheimer’s & Dementia, 19(10), 4705-4728. https://doi.org/10.1002/alz.13369
