Use of Speech Analyses within a Mobile Application for the Assessment of Cognitive Impairment in Elderly People

König, Alexandra; Satt, Aharon; Sorin, Alex; Hoory, Ran; Derreumaux, Alexandre; David, Renaud; Robert, Phillippe

doi:10.2174/1567205014666170829111942

Cited by 98 publications

(101 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Automated analysis of speech, in particular speech that is produced during a standard clinical assessment, might be a prime candidate for such a tool [9-14]. Several research groups demonstrated the interest of adopting an automated approach to speech analysis for clinical assessment of older people [15-19]. Overall, reported work either uses speech from conversations, spontaneous speech tasks, reading or repetition tasks, and fluency tasks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully Automatic Speech-Based Analysis of the Semantic Verbal Fluency Task

König

Linz

Tröger

et al. 2018

Dement Geriatr Cogn Disord

View full text Add to dashboard Cite

Background: Semantic verbal fluency (SVF) tests are routinely used in screening for mild cognitive impairment (MCI). In this task, participants name as many items as possible of a semantic category under a time constraint. Clinicians measure task performance manually by summing the number of correct words and errors. More fine-grained variables add valuable information to clinical assessment, but are time-consuming. Therefore, the aim of this study is to investigate whether automatic analysis of the SVF could provide these as accurate as manual and thus, support qualitative screening of neurocognitive impairment. Methods: SVF data were collected from 95 older people with MCI (n = 47), Alzheimer’s or related dementias (ADRD; n = 24), and healthy controls (HC; n = 24). All data were annotated manually and automatically with clusters and switches. The obtained metrics were validated using a classifier to distinguish HC, MCI, and ADRD. Results: Automatically extracted clusters and switches were highly correlated (r = 0.9) with manually established values, and performed as well on the classification task separating HC from persons with ADRD (area under curve [AUC] = 0.939) and MCI (AUC = 0.758). Conclusion: The results show that it is possible to automate fine-grained analyses of SVF data for the assessment of cognitive decline.

show abstract

Section: Introductionmentioning

confidence: 99%

“…annotating turns, or trimming the audio file, in order to prepare it for further computational learning which is not useful for an application in daily clinical practice. Moreover, in order to detect in speech early subtle changes of cognition, it seems crucial to induce a minimum of cognitive effort in a vocal task [15, 20]. …”

Section: Introductionmentioning

confidence: 99%

Fully Automatic Speech-Based Analysis of the Semantic Verbal Fluency Task

König

Linz

Tröger

et al. 2018

Dement Geriatr Cogn Disord

View full text Add to dashboard Cite

show abstract

“…Similar results were found in [12], where acoustic features extracted from speech recordings provided high accuracy rates in classifying healthy versus AD (87%), MCI versus AD (80%), and healthy versus MCI (79%). Even higher classification accuracies were found in a subsequent work of the same group, in which speech analysis was performed on a mobile application, but still in a controlled environment [13].…”

Section: Introductionmentioning

confidence: 75%

Automatic speech analysis to early detect functional cognitive decline in elderly population

Ambrosini

Caielli

Milis

et al. 2019

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

“…In a parallel study, the same research group (König et al, 2017) introduced a technology for speech analyses for the assessment of cognitive impairment in older adults. They recorded 165 participants with subjective cognitive impairment (SCI), MCI, AD and mixed dementia with a mobile application while they performed a range of verbal tasks, including verbal fluency.…”

Section: Verbal Fluency Tasksmentioning

confidence: 99%

Marrying Past and Present Neuropsychology: Is the Future of the Process-Based Approach Technology-Based?

et al. 2020

View full text Add to dashboard Cite

A cognitive assessment strategy that is not limited to examining a set of summary test scores may be more helpful for early detection of emergent illness such as Alzheimer's disease (AD) and may permit a better understanding of cognitive functions and dysfunctions in those with AD and other dementia disorders. A revisit of the work already undertaken by Kaplan and colleagues using the Boston Process-Approach provides a solid basis for identifying new opportunities to capture data on neurocognitive processes, test-taking strategies and response styles. Thus, this critical review will combine traditional process-based assessment strategies with support provided or offered by newer technologies that have the potential to add value to data collection and interpretation. There is now considerable interest in neuropsychological test administration using computer/digital technology, both in research and in clinical settings. To add value, any computerized version of an existing cognitive test should respect the administration procedure for which normative data were obtained, should be time-saving in terms of scoring and interpretation, and should, we argue, facilitate gathering information about the processes and strategies followed in test completion. This article will offer an overview of the steps needed when implementing computerization of neuropsychological tests using a Process-Based Approach (PBA) to these technology-based adaptations and will discuss further developments in this area by linking it to future technological developments that may be possible in the area of neuropsychological assessment. Additionally, an overview of neuropsychological tests that may benefit from computerization will be presented, together with suggestions on the specific processes, strategies and features that may be captured with the aid of such computerization. Finally, hypotheses on how virtual reality could be an asset for the future of the PBA to neuropsychological assessment will also be discussed.

show abstract

Use of Speech Analyses within a Mobile Application for the Assessment of Cognitive Impairment in Elderly People

Cited by 98 publications

References 0 publications

Fully Automatic Speech-Based Analysis of the Semantic Verbal Fluency Task

Fully Automatic Speech-Based Analysis of the Semantic Verbal Fluency Task

Automatic speech analysis to early detect functional cognitive decline in elderly population

Marrying Past and Present Neuropsychology: Is the Future of the Process-Based Approach Technology-Based?

Contact Info

Product

Resources

About