Cited by 32Dementia and Cognitive Impairment ResearchContext-Aware Activity Recognition SystemsHuman Pose and Action Recognition

Automatic video monitoring system for assessment of Alzheimer's disease symptoms

Open access
Romdhane, R., Mulin, E., Derreumeaux, A., Zouba, N., Piano, J., Lee, L., Leroi, I., Mallea, P. +4 more·2012·The Journal of nutrition, health and aging

Abstract

In order to fully capture the complexity of the behavioural, functioning and cognitive disturbances in Alzheimer Disease (AD) and related disorders information and communication techniques (ICT), could be of interest. This article presents using 3 clinical cases the feasibility results of an automatic video monitoring system aiming to assess subjects involved in a clinical scenario. METHOD AND POPULATION: The study was conducted in an observation room equipped with everyday objects for use in activities of daily living. The overall aim of the clinical scenario was to enable the participants to undertake a set of daily tasks that could realistically be achieved in the setting of the observation room. The scenario was divided in three steps covering basic to more complex activities: (1) Directed activities, (2) Semi-directed activities, (3) Undirected ("free") activities. The assessment of each participant of the study was done with an automatic video monitoring system composed of a vision component and an event recognition component. The feasibility study involved three participants: two AD patients and one elderly control participant. RESULTS: The first result of the study was to demonstrate the feasibility of this new assessment method from both the patient and the technical points of view. During the first step the control participant performed all these activities faster than the two AD participants. During the second step of the scenario AD participants were not able to follow the correct order of the tasks and even omitted some of them. Finally during the last step of the scenario devoted to free activities the control participant chose one of the proposed activities (reading) and undertook this activity for almost the entire duration. In contrast, the two AD participants had more difficulties choosing one of the suggested activities and were not able to undertake any one activity in a sustained manner. DISCUSSION: The automatic video monitoring system presented here analyzes human behaviours and looks for changes in activity through the detection of the presence of people and their movements in real time. Once the technique has been standardized, it could significantly enhance the assessment of AD patients in both clinical and clinical trial settings as well as providing further information regarding patient frailty that could enhance their safety and ease caregiver burden.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s12603-012-0039-7

Cites

19 of 19 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Romdhane, R., Mulin, E., Derreumeaux, A., Zouba, N., Piano, J., Lee, L., Leroi, I., Mallea, P., David, R., Thonnat, M., Bremond, F., & Robert, P. H.
Affiliations
  • Institut national de recherche en sciences et technologies du numérique (FR)
  • Centre Hospitalier Universitaire de Nice (FR)
  • University of Manchester (GB)
Corresponding author
Robert, P.H.
Venue
The Journal of nutrition, health and aging
Publisher
Elsevier BV
Published
2012-03
Volume
16
Issue
3
Pages
213-218
ISSN
1279-7707 (ISSN-L)
OpenAlex
W2164567451
Cited by
32
References
19
Citations by year
2026: 1 · 2023: 1 · 2022: 1 · 2021: 1 · 2019: 2 · 2018: 1 · 2016: 4 · 2015: 6 · 2014: 3 · 2013: 7 · 2012: 3
FWCI
4.33
Type
journal article
Language
en
Open access
Locations
  • The journal of nutrition health & aging (publishedVersion, cc-by-nc-nd)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • Research Explorer (The University of Manchester) (publishedVersion)
  • HAL (submittedVersion, other-oa)
Funders
Agence Nationale de la Recherche (ANR-09-TECS-0016)
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
Keywords
Alzheimer's disease, activities of daily living, event recognition, real-time human detection, human motion analysis, behavioral assessment, clinical trial monitoring, patient frailty, caregiver burden, older adults
MeSH terms
Activities of Daily Living, Aged, Alzheimer Disease, Feasibility Studies, Female, Humans, Male, Neuropsychological Tests, Population Surveillance, Severity of Illness Index, Video Recording, Diagnostic and Statistical Manual of Mental Disorders

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review