Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Dec 18;6(1):234.
doi: 10.1038/s41746-023-00978-6.

Augmented reality versus standard tests to assess cognition and function in early Alzheimer's disease

Marijn Muurling  1   2 , Casper de Boer  3   4 , Srinivasan Vairavan  5 , Robbert L Harms  6 , Antonella Santuccione Chadha  6 , Ioannis Tarnanas  6   7 , Estefania Vilarino Luis  8 , Dorota Religa  9 , Martha Therese Gjestsen  10   11 , Samantha Galluzzi  12 , Marta Ibarria Sala  13 , Ivan Koychev  14 , Lucrezia Hausner  15 , Mara Gkioka  16 , Dag Aarsland  10   17 , Pieter Jelle Visser  3   4   9   18 , Anna-Katharine Brem  17   19
Affiliations

Augmented reality versus standard tests to assess cognition and function in early Alzheimer's disease

Marijn Muurling et al. NPJ Digit Med. .

Abstract

Augmented reality (AR) apps, in which the virtual and real world are combined, can recreate instrumental activities of daily living (IADL) and are therefore promising to measure cognition needed for IADL in early Alzheimer's disease (AD) both in the clinic and in the home settings. The primary aim of this study was to distinguish and classify healthy controls (HC) from participants with AD pathology in an early AD stage using an AR app. The secondary aims were to test the association of the app with clinical cognitive and functional tests and investigate the feasibility of at-home testing using AR. We furthermore investigated the test-retest reliability and potential learning effects of the task. The digital score from the AR app could significantly distinguish HC from preclinical AD (preAD) and prodromal AD (proAD), and preAD from proAD, both with in-clinic and at-home tests. For the classification of the proAD group, the digital score (AUCclinic_visit = 0.84 [0.75-0.93], AUCat_home = 0.77 [0.61-0.93]) was as good as the cognitive score (AUC = 0.85 [0.78-0.93]), while for classifying the preAD group, the digital score (AUCclinic_visit = 0.66 [0.53-0.78], AUCat_home = 0.76 [0.61-0.91]) was superior to the cognitive score (AUC = 0.55 [0.42-0.68]). In-clinic and at-home tests moderately correlated (rho = 0.57, p < 0.001). The digital score was associated with the clinical cognitive score (rho = 0.56, p < 0.001). No learning effects were found. Here we report the AR app distinguishes HC from otherwise healthy Aβ-positive individuals, both in the outpatient setting and at home, which is currently not possible with standard cognitive tests.

PubMed Disclaimer

Conflict of interest statement

R.L.H., A.S.C. and I.T. are employees of Altoida Inc. and declare no non-financial competing interests. S.V. is an employee of Janssen Pharmaceutical NV and may hold stock options or shares in the company, but has no non-financial competing interests. D.A. has received research support and/or honoraria from Astra-Zeneca, H. Lundbeck, Novartis Pharmaceuticals, Biogen, and GE Health, and served as a paid consultant for H. Lundbeck, Eisai, Heptares, Mentis Cura, and Roche Diagnostics, but declares no non-financial competing interests. S.G. declares support for this work through the Italian Ministry of Health (Ricerca Corrente). All other authors declare no financial or non-financial competing interests.

Figures

Fig. 1
Fig. 1. Digital scores from the AR app presented per study group.
a In-clinic test (N = 121). b At-home test (N = 56). Each dot represents the digital score of one participant. The box represents the lower and upper quartiles with the center line the median, and the whiskers represent the minimum and maximum score. Group differences were tested using a linear model, corrected for app version and site. **p < 0.01, ***p < 0.001, ns indicates not significant. HC healthy control, preAD preclinical AD, proAD prodromal AD.
Fig. 2
Fig. 2. ROC curves for the digital in-clinic, digital at-home, cognitive, and A-IADL score.
a Classification of healthy controls relative to preclinical AD. b Classification of healthy controls relative to prodromal AD. Black line shows digital in-clinic test curve, red line shows digital at-home test curve, green lines shows cognitive score curve, and light blue line shows A-IADL score curve. A-IADL Amsterdam instrumental activities of daily living, HC healthy control, PreAD Preclinical AD, ProAD Prodromal AD.
Fig. 3
Fig. 3. Association of digital score with standard tests.
a Association of digital score (in-clinic) with the cognitive score (Spearman’s rho = 0.56, p < 0.001). b Association of digital score (in-clinic) with the A-IADL score (Spearman’s rho = 0.43, p < 0.001). Each dot represents the scores of one participant. The black solid line represents the correlation line with the 95% confidence interval in gray. A-IADL Amsterdam instrumental activities of daily living.
Fig. 4
Fig. 4. Within-subject associations.
a Correlation between in-clinic and at-home tests (HC: rho = 0.34, p = 0.07; preAD: rho = 0.54, p = 0.06; proAD: rho = 0.58, p = 0.03). Each dot represents the digital score from one participant. The black dashed line is the rho = 1 line. The black solid line shows the correlation line with the 95% confidence interval in gray. b Change of digital score over time. Each line represents one participant. The black solid line represents the average change over time with the 95% confidence interval in gray. Prodromal AD participants showed overall lower scores, but no learning effects were seen. HC healthy control, PreAD Preclinical AD, ProAD Prodromal AD.
Fig. 5
Fig. 5. Flow diagram of the participant population included in this study.
AR tasks were not finished because of the following reasons: (1) “Participant was unable to”: due to physical or cognitive problems the participant was unable to finish the test rounds successfully, (2) “Technical issues”: the app or device did not work as expected, (3) “Not enough time”: there was not enough time during the baseline visit to execute the tasks, (4) “Other reasons”: unspecified, unknown, or other reasons. AD Alzheimer’s disease, AR augmented reality, HC healthy control, RADAR-AD Remove Assessment of Disease and Relapse – Alzheimer’s Disease, preAD preclinical AD, proAD prodromal AD.
Fig. 6
Fig. 6
Examples of representative screenshots and task descriptions of the motor tasks (01 and 02) and AR tasks (03) in the Altoida app.
See this image and copyright information in PMC

References

    1. Sperling RA, et al. Toward defining the preclinical stages of Alzheimer’s disease: recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimers Dement. 2011;7:280–292. doi: 10.1016/j.jalz.2011.03.003. - DOI - PMC - PubMed
    1. Lawton MP, Brody EM. Assessment of older people: self-maintaining and instrumental activities of daily living. Gerontologist. 1969;9:179–186. doi: 10.1093/geront/9.3_Part_1.179. - DOI - PubMed
    1. Dubbelman MA, et al. Trajectories of decline in cognitively complex everyday activities across the Alzheimer’s disease continuum: Neuropsychology: Longitudinal cognitive assessment in early stages of AD. Alzheimers Dement. 2020;16:e044787. doi: 10.1002/alz.044787. - DOI
    1. Jutten RJ, et al. Detecting functional decline from normal aging to dementia: development and validation of a short version of the Amsterdam IADL Questionnaire. Alzheimers Dement. (Amst). 2017;8:26–35. doi: 10.1016/j.dadm.2017.03.002. - DOI - PMC - PubMed
    1. Jekel K, et al. Mild cognitive impairment and deficits in instrumental activities of daily living: a systematic review. Alzheimers Res. Ther. 2015;7:1–20. doi: 10.1186/s13195-015-0099-0. - DOI - PMC - PubMed