Detecting and Monitoring Behavioural Patterns in Individuals with Cognitive Disorders in the Home Environment with Partial Annotations

Wu, Yang; Poyiadzi, Rafael; Ben‐Shlomo, Yoav; Craddock, Ian J; Coulthard, Liz; Santos-Rodríguez, Raúl; Selwood, James; Twomey, Niall

doi:10.1007/978-3-030-91181-2_3

Cited by 3 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is somewhat consistent with the literature because ambient smart home systems have been used in multiple cohorts to measure IADLs [ 53 , 54 ]; for example, the Sensor Platform for Healthcare in a Residential Environment (SPHERE) system, which has been used to monitor IADL-related behaviors in people with Parkinson disease, comprises a wrist-worn accelerometer alongside multiple environmental sensors (including motion sensors similar to those found in this review) that can also assess energy consumption, humidity, and temperature [ 55 ]. This system has been extended to groups with cognitive impairment in current pilot work with people with MCI and Alzheimer disease [ 56 ]. Other research has collected more discrete targeted IADL-related behaviors; for example, analog sensors that measure energy consumption have been used to capture cooking activities such as stove burner use [ 57 ].…”

Section: Discussionmentioning

confidence: 99%

Digital Endpoints for Assessing Instrumental Activities of Daily Living in Mild Cognitive Impairment: Systematic Review

Lawson¹,

Ardle²,

Wilson³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background Subtle impairments in instrumental activities of daily living (IADLs) can be a key predictor of disease progression and are considered central to functional independence. Mild cognitive impairment (MCI) is a syndrome associated with significant changes in cognitive function and mild impairment in complex functional abilities. The early detection of functional decline through the identification of IADL impairments can aid early intervention strategies. Digital health technology is an objective method of capturing IADL-related behaviors. However, it is unclear how these IADL-related behaviors have been digitally assessed in the literature and what differences can be observed between MCI and normal aging. Objective This review aimed to identify the digital methods and metrics used to assess IADL-related behaviors in people with MCI and report any statistically significant differences in digital endpoints between MCI and normal aging and how these digital endpoints change over time. Methods A total of 16,099 articles were identified from 8 databases (CINAHL, Embase, MEDLINE, ProQuest, PsycINFO, PubMed, Web of Science, and Scopus), out of which 15 were included in this review. The included studies must have used continuous remote digital measures to assess IADL-related behaviors in adults characterized as having MCI by clinical diagnosis or assessment. This review was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Results Ambient technology was the most commonly used digital method to assess IADL-related behaviors in the included studies (14/15, 93%), with passive infrared motion sensors (5/15, 33%) and contact sensors (5/15, 33%) being the most prevalent types of methods. Digital technologies were used to assess IADL-related behaviors across 5 domains: activities outside of the home, everyday technology use, household and personal management, medication management, and orientation. Other recognized domains—culturally specific tasks and socialization and communication—were not assessed. Of the 79 metrics recorded among 11 types of technologies, 65 (82%) were used only once. There were inconsistent findings around differences in digital IADL endpoints across the cognitive spectrum, with limited longitudinal assessment of how they changed over time. Conclusions Despite the broad range of metrics and methods used to digitally assess IADL-related behaviors in people with MCI, several IADLs relevant to functional decline were not studied. Measuring multiple IADL-related digital endpoints could offer more value than the measurement of discrete IADL outcomes alone to observe functional decline. Key recommendations include the development of suitable core metrics relevant to IADL-related behaviors that are based on clinically meaningful outcomes to aid the standardization and further validation of digital technologies against existing IADL measures. Increased longitudinal monitoring is necessary to capture changes in digital IADL endpoints over time in people with MCI. Trial Registration PROSPERO International Prospective Register of Systematic Reviews CRD42022326861; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=326861

show abstract

Section: Discussionmentioning

confidence: 99%

Digital Endpoints for Assessing Instrumental Activities of Daily Living in Mild Cognitive Impairment: Systematic Review

Lawson¹,

Ardle²,

Wilson³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…In these settings, a particularly important task is that of localisation which is helpful for quantifying behaviours in the home environment (D'Souza, Ros, and Karunanithi 2012; Otsason et al 2005;Klingbeil and Wark 2008). Our realworld data is collected from a similar smart home project (Yang et al 2022). For the localisation task, we have access to room-level annotations.…”

Section: Real-world Datasetmentioning

confidence: 99%

Hypothesis Testing for Class-Conditional Noise Using Local Maximum Likelihood

Yang,

Poyiadzi,

Twomey

et al. 2024

AAAI

View full text Add to dashboard Cite

In supervised learning, automatically assessing the quality of the labels before any learning takes place remains an open research question. In certain particular cases, hypothesis testing procedures have been proposed to assess whether a given instance-label dataset is contaminated with class-conditional label noise, as opposed to uniform label noise. The existing theory builds on the asymptotic properties of the Maximum Likelihood Estimate for parametric logistic regression. However, the parametric assumptions on top of which these approaches are constructed are often too strong and unrealistic in practice. To alleviate this problem, in this paper we propose an alternative path by showing how similar procedures can be followed when the underlying model is a product of Local Maximum Likelihood Estimation that leads to more flexible nonparametric logistic regression models, which in turn are less susceptible to model misspecification. This different view allows for wider applicability of the tests by offering users access to a richer model class. Similarly to existing works, we assume we have access to anchor points which are provided by the users. We introduce the necessary ingredients for the adaptation of the hypothesis tests to the case of nonparametric logistic regression and empirically compare against the parametric approach presenting both synthetic and real-world case studies and discussing the advantages and limitations of the proposed approach.

show abstract

Digital Endpoints for Assessing Instrumental Activities of Daily Living in Mild Cognitive Impairment: Systematic Review (Preprint)

Lawson¹,

Ardle²,

Wilson³

et al. 2023

Preprint

View full text Add to dashboard Cite

BACKGROUND Subtle impairments in instrumental activities of daily living (IADLs) can be a key predictor of disease progression and are considered central to functional independence. Mild cognitive impairment (MCI) is a syndrome associated with significant changes in cognitive function and mild impairment in complex functional abilities. The early detection of functional decline through the identification of IADL impairments can aid early intervention strategies. Digital health technology is an objective method of capturing IADL-related behaviors. However, it is unclear how these IADL-related behaviors have been digitally assessed in the literature and what differences can be observed between MCI and normal aging. OBJECTIVE This review aimed to identify the digital methods and metrics used to assess IADL-related behaviors in people with MCI and report any statistically significant differences in digital endpoints between MCI and normal aging and how these digital endpoints change over time. METHODS A total of 16,099 articles were identified from 8 databases (CINAHL, Embase, MEDLINE, ProQuest, PsycINFO, PubMed, Web of Science, and Scopus), out of which 15 were included in this review. The included studies must have used continuous remote digital measures to assess IADL-related behaviors in adults characterized as having MCI by clinical diagnosis or assessment. This review was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. RESULTS Ambient technology was the most commonly used digital method to assess IADL-related behaviors in the included studies (14/15, 93%), with passive infrared motion sensors (5/15, 33%) and contact sensors (5/15, 33%) being the most prevalent types of methods. Digital technologies were used to assess IADL-related behaviors across 5 domains: activities outside of the home, everyday technology use, household and personal management, medication management, and orientation. Other recognized domains—culturally specific tasks and socialization and communication—were not assessed. Of the 79 metrics recorded among 11 types of technologies, 65 (82%) were used only once. There were inconsistent findings around differences in digital IADL endpoints across the cognitive spectrum, with limited longitudinal assessment of how they changed over time. CONCLUSIONS Despite the broad range of metrics and methods used to digitally assess IADL-related behaviors in people with MCI, several IADLs relevant to functional decline were not studied. Measuring multiple IADL-related digital endpoints could offer more value than the measurement of discrete IADL outcomes alone to observe functional decline. Key recommendations include the development of suitable core metrics relevant to IADL-related behaviors that are based on clinically meaningful outcomes to aid the standardization and further validation of digital technologies against existing IADL measures. Increased longitudinal monitoring is necessary to capture changes in digital IADL endpoints over time in people with MCI. CLINICALTRIAL PROSPERO International Prospective Register of Systematic Reviews CRD42022326861; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=326861

show abstract

Detecting and Monitoring Behavioural Patterns in Individuals with Cognitive Disorders in the Home Environment with Partial Annotations

Cited by 3 publications

References 54 publications

Digital Endpoints for Assessing Instrumental Activities of Daily Living in Mild Cognitive Impairment: Systematic Review

Digital Endpoints for Assessing Instrumental Activities of Daily Living in Mild Cognitive Impairment: Systematic Review

Hypothesis Testing for Class-Conditional Noise Using Local Maximum Likelihood

Digital Endpoints for Assessing Instrumental Activities of Daily Living in Mild Cognitive Impairment: Systematic Review (Preprint)

Contact Info

Product

Resources

About