Language Performance of Individuals at Risk for Mild Cognitive Impairment

McCullough, Kim; Bayles, Kathryn A.; Bouldin, Erin D.

doi:10.1044/2018_jslhr-l-18-0232

Cited by 40 publications

(27 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…architectures [32] can analyze language produced by individuals (e.g., patients and healthy subjects) to distinguish healthy subjects from patients with dementia. In more details, the ML algorithms can be trained by linguistic features to identify language performance deficits in elderly individuals [26,29,30,49]. One of the earliest studies to develop such an ML algorithm was proposed using the SVM to detect voice impairments in patients with AD [28].…”

Section: Classifiermentioning

confidence: 99%

“…These signs are associated to Language and Communication Impairment in patients with dementia. In particular, LA tools that analyze spontaneous speech, produced during the completion of cognitive tasks [25] can recognize linguistic features associated with language performance deficits in elderly individuals [26]. Therefore, they are efficient methods to diagnose AD/MCI in elderly adults [27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards AI-powered Language Assessment Tools

Parsa¹,

Alam²,

Mihailidis³

2021

Preprint

View full text Add to dashboard Cite

Objectives: The main objective of this paper is to propose an approach for developing an Artificial Intelligence (AI)-powered Language Assessment (LA) tool. Such tools can be used to assess language impairments associated with dementia in older adults. The Machine Learning (ML) classifiers are the main parts of our proposed approach, therefore to develop an accurate tool with high sensitivity and specificity, we consider different binary classifiers and evaluate their performances. We also assess the reliability and validity of our approach by comparing the impact of different types of language tasks, features, and recording media on the performance of ML classifiers. Approach: Our approach includes the following steps: 1) Collecting language datasets or getting access to available language datasets; 2) Extracting linguistic and acoustic features from subjects' speeches which have been collected from subjects with dementia (N=9) and subjects without dementia (N=13); 3) Selecting most informative features and using them to train ML classifiers; and 4) Evaluating the performance of classifiers on distinguishing subjects with dementia from subjects without dementia and select the most accurate classier to be the basis of the AI tool. Results: Our results indicate that 1) we can nd more predictive linguistic markers to distinguish language impairment associated with dementia from participants' speech produced during the Picture Description (PD) language task than the Story Recall (SR) task; and 2) phone-based recording interfaces provide more high-quality language datasets than the web-based recording systems Conclusion: Our results verify that the tree-based classifiers, which have been trained using the linguistic and acoustic features extracted from interviews' transcript and audio, can be used to develop an AI-powered language assessment tool for detecting language impairment associated with dementia.

show abstract

Section: Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Towards AI-powered Language Assessment Tools

Parsa¹,

Alam²,

Mihailidis³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…These signs are associated to Language and Communication Impairment (LCI) in patients with dementia. In particular, LA tools that analyze spontaneous speech, produced during the completion of cognitive tasks [46] can recognize linguistic features associated with language performance deficits in elderly individuals [47]. Therefore, they are efficient methods to diagnose AD/MCI in elderly adults [48].…”

Section: Language Assessment Toolsmentioning

confidence: 99%

“…So far, various ML algorithms (such as k-Nearest Neighbor (kNN) [13], Support Vector Machine (SVM), Decision Trees (DTs) [13,14] and Random Forest (RF) classifiers [49] as well as Deep Learning (DL) architectures [16] have been examined to distinguish patients from healthy subjects. In more details, the ML algorithms have been trained by linguistic features to identify language performance deficits in elderly individuals [47,13,14,49]. One of the earliest studies to develop such an ML algorithm was proposed using the SVM to detect voice impairments in patients with AD [12].…”

Section: Machine Learningmentioning

confidence: 99%

Machine Learning to Assess Language Impairments in Older Adults

Parsa¹,

Alam²,

Mihailidis³

2020

Preprint

View full text Add to dashboard Cite

Objectives: The main objective of this paper is to propose a methodology based on machine learning classifiers for assessing language impairments associated with dementia in older adults. To do so, we compare the impact of different types of language tasks, features, and recording media on our ML-based methodology’s efficiency. Methodology: The methodology encompasses the following steps: 1) Extracting linguistic and acoustic features from subjects’ speeches which have been collected from subjects with dementia ( N =9) and subjects without dementia ( N =13); 2) Employing feature selection methods to rank informative features; 3) Training ML classifiers using extracted features to recognize subjects with dementia from subjects without dementia; 4) Evaluating the classifiers; 5) Selecting the most accurate classifiers to develop the languages assessment tools. Results: Our results indicate that 1) we can find more predictive linguistic markers to distinguish language impairment associated with dementia from participants’ speech produced during the picture description language task than the story recall task. 2) a phone-based recording interface provides a more high-quality language dataset than the web-based recording systems; 3) classifiers trained with selected features from acoustic features or linguistic features show higher performance than the classifiers trained with pure features. Conclusion: Our results show that the tree-based classifiers that have been trained using the PD dataset can be used to develop an ML-based language assessment tool that can detect language impairment associated with dementia as quickly as possible.

show abstract

“…25 Most neuropsychological studies involving MCI have focused on disorders of episodic memory, language, and executive functions. [26][27][28][29][30][31] Actually, information processing speed is included in the diagnostic criteria for neurocognitive disorders of the Diagnostic and Statistical Manual of Mental Disorders (DSM-5). 16 However, there is substantially less research that evaluates deficits in PS in MCI.…”

Section: Introductionmentioning

confidence: 99%

Diagnostic accuracy of early cognitive indicators in mild cognitive impairment

Martorelli

Hartle

Coutinho

et al. 2020

Dement. neuropsychol.

View full text Add to dashboard Cite

The aging of the population leads to an increase in the prevalence of dementia and mild cognitive impairment (MCI). Alzheimer's disease (AD) is the most common cause of dementia. Recent studies highlight the early non-amnestic deficits in AD and MCI. The European Union report shows the importance of thoroughly assessing cognitive aspects that have been poorly evaluated, such as processing speed (PS), which could represent early indicators of cognitive decline. Objective: To analyze the diagnostic accuracy of PS measures in older adults with MCI, AD, and those who are cognitively-healthy. Methods: A cross-sectional study was conducted by performing an extensive neuropsychological assessment in three samples: 26 control participants, 22 individuals with MCI, and 21 individuals with AD. Analysis of variance (ANOVA) was employed to test the relationship between dependent variables and the clinical group. Post hoc tests (Bonferroni test) were used when a significant ANOVA result was found. Finally, the Receiver Operating Characteristic (ROC) curve for PS measures was performed in older adults with MCI and AD compared with cognitively-healthy older adults. Results: The results showed that deficits in PS measures can be early indicators of cognitive decline in cases of MCI, even when executive functions (EFs) and functionality are preserved. Conversely, AD versus MCI presented differences in PS, EFs, and functionality. Conclusions: The ROC analyses showed that PS measures had discriminative capacities to differentiate individuals with MCI, AD, and cognitively-healthy older adults.

show abstract

Language Performance of Individuals at Risk for Mild Cognitive Impairment

Cited by 40 publications

References 105 publications

Towards AI-powered Language Assessment Tools

Towards AI-powered Language Assessment Tools

Machine Learning to Assess Language Impairments in Older Adults

Diagnostic accuracy of early cognitive indicators in mild cognitive impairment

Contact Info

Product

Resources

About