Can you detect early dementia from an email? A proof of principle study of daily computer use to detect cognitive and functional decline

Stringer, Gemma; Couth, Samuel; Brown, Laura J. E.; Montaldi, Daniela; Gledson, Ann; Mellor, Joseph; Sutcliffe﻿, Alistair; Sawyer, Pete; Keane, John; Bull, Christopher; Zeng, Xiao‐Jun; Rayson, Paul; Leroi, Iracema

doi:10.1002/gps.4863

Cited by 32 publications

(23 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Older people (over the age of 65 years) with SCD, MCI, and mild dementia due to AD were recruited for steps 1 and 3 through memory clinics; the UK dementia research registry "Join Dementia Research" (a national web-based service for participation in dementia studies); step 3 participants were also part of another study called Software Architecture for Mental Health Self-Management (SAMS) (Stringer et al, 2018). Participants with dementia and MCI diagnoses were referred with a diagnosis already made by qualified memory specialists.…”

Section: Participantsmentioning

confidence: 99%

“…Participants with self-reported worries about their memory were identified as SCD if they indicated on a scale of functional capacitythe Everyday Cognition Scale (ECog) (Farias et al, 2008) that they were "concerned they have a memory or other thinking problem" and their total score on this scale was >1.436. This cutoff score corresponds to the upper 95% confidence interval of the mean total ECog scores from a sample of healthy control participants who indicated that they were not "concerned they have a memory or other thinking problem" (Stringer et al, 2018). Participants who did not meet this criterion for SCD were not eligible to take part.…”

Section: Participantsmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing ‘meaningfulness’ of functional assessments: UK adaptation of the Amsterdam IADL questionnaire

Stringer

Leroi

Sikkes

et al. 2020

Int. Psychogeriatr.

Self Cite

View full text Add to dashboard Cite

Objective: Commonly used measures of instrumental activities of daily living (IADL) do not capture activities for a technologically advancing society. This study aimed to adapt the proxy/informant-based Amsterdam IADL Questionnaire (A-IADL-Q) for use in the UK and develop a self-report version.Design: An iterative mixed method cross-cultural adaptation of the A-IADL-Q and the development of a self-report version involving a three-step design: (1) interviews and focus groups with lay and professional stakeholders to assess face and content validity; (2) a questionnaire to measure item relevance to older adults in the U.K.; (3) a pilot of the adapted questionnaire in people with cognitive impairment.Setting: Community settings in the UK.Participants: One hundred and forty-eight participants took part across the three steps: (1) 14 dementia professionals; 8 people with subjective cognitive decline (SCD), mild cognitive impairment (MCI), or dementia due to Alzheimer's disease; and 6 relatives of people with MCI or dementia; (2) 92 older adults without cognitive impairment; and (3) 28 people with SCD or MCI. Measurements:The cultural relevance and applicability of the A-IADL-Q scale items were assessed using a 6-point Likert scale. Cognitive and functional performance was measured using a battery of cognitive and functional measures.Results: Iterative modifications to the scale resulted in a 55-item adapted version appropriate for UK use (A-IADL-Q-UK). Pilot data revealed that the new and revised items performed well. Four new items correlated with the weighted average score ). An exploratory analysis of convergent validity found correlations in the expected direction with cognitive and functional measures. Conclusion:The A-IADL-Q-UK provides a measurement of functional decline for use in the UK that captures culturally relevant activities. A new self-report version has been developed and is ready for testing. Further evaluation of the A-IADL-Q-UK for construct validity is now needed.

show abstract

Section: Participantsmentioning

confidence: 99%

Section: Participantsmentioning

confidence: 99%

Enhancing ‘meaningfulness’ of functional assessments: UK adaptation of the Amsterdam IADL questionnaire

Stringer

Leroi

Sikkes

et al. 2020

Int. Psychogeriatr.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Significant resources are being invested in developing new assistive and diagnostic technologies for the elderly or those living with dementia (e.g. [10], [11]) as increasing life expectancy leads to increases in the incidence of dementia. The potential health-related benefits offered by technology are counterweighted by societal, legal and ethical challenges [14] and many governments are seeking to define forwardlooking policies on dementia care (e.g.…”

Section: The 'What If?' Case Studymentioning

confidence: 99%

Speculative Requirements: Design Fiction and RE

Darby

Tsekleves

Sawyer

2018

2018 IEEE 26th International Requirements Engineering Conference (RE)

View full text Add to dashboard Cite

Many innovative software products are conceived, developed and deployed without any conventional attempt to elicit stakeholder requirements. Rather, they are the result of the vision and intuition of a small number of creative individuals, facilitated by the emergence of a new technology. In this paper we consider how the conditions that enable new products' emergence might be better anticipated, making innovations a little less reliant on individual vision and a little more informed by stakeholder need. This is particularly important where a new technology would have the potential for social impact, good or bad. Speculative design seeks to explore this landscape. We describe a case study using a variant called design fiction to explore how plausible new technologies might impact on dementia care.

show abstract

“…Other modalities aside from voice has also been investigated and found to be good predictors for cognitive decline and dementia including eye movement Parsons et al (2017); Zhang et al (2016), olfactory Karunanayaka et al (2017); Lafaille-Magnan et al (2015) and even hand dexterity Stringer et al (2018).…”

Section: Introductionmentioning

confidence: 99%

Dementia detection using automatic analysis of conversations

Mirheidari

Blackburn

Walker

et al. 2019

Computer Speech & Language

View full text Add to dashboard Cite

Neurogenerative disorders, like dementia, can affect a person's speech, language and as a consequence, conversational interaction capabilities. A recent study, aimed at improving dementia detection accuracy, investigated the use of conversation analysis (CA) of interviews between patients and neurologists as a means to differentiate between patients with progressive neurodegenerative memory disorder (ND) and those with (non-progressive) functional memory disorders (FMD). However, manual CA is expensive and difficult to scale up for routine clinical use. In this paper, we present an automatic classification using an intelligent virtual agent (IVA). In particular, using two parallel corpora of respectively neurologist-and IVA-led interactions, we show that using acoustic, lexical and CA-inspired features enables ND/FMD classification rates of 90.0% for the neurologist-patient conversations, and an encouraging 90.9% for the IVApatient conversations. Analysis of the significance of individual features show that some differences exist between the IVA and human-led conversations for example in average turn length of patients.

show abstract

Can you detect early dementia from an email? A proof of principle study of daily computer use to detect cognitive and functional decline

Cited by 32 publications

References 22 publications

Enhancing ‘meaningfulness’ of functional assessments: UK adaptation of the Amsterdam IADL questionnaire

Enhancing ‘meaningfulness’ of functional assessments: UK adaptation of the Amsterdam IADL questionnaire

Speculative Requirements: Design Fiction and RE

Dementia detection using automatic analysis of conversations

Contact Info

Product

Resources

About