Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index; 1 of the 4 sources its claims cite were checked for support.

Chatbots to Support People With Dementia and Their Caregivers: Systematic Review of Functions and Quality

Open access
Ruggiano, Nicole, Brown, Ellen L, Roberts, Lisa, Framil Suarez, C Victoria, Luo, Yan, Hao, Zhichao, Hristidis, Vagelis · 2021 · Journal of Medical Internet Research

Published version of a preprint

Abstract

BACKGROUND: Over the past decade, there has been an increase in the use of information technologies to educate and support people with dementia and their family caregivers. At the same time, chatbot technologies have become increasingly popular for use by the public and have been identified as having benefits for health care delivery. However, little is known about how chatbot technologies may benefit people with dementia and their caregivers. OBJECTIVE: This study aims to identify the types of current commercially available chatbots that are designed for use by people with dementia and their caregivers and to assess their quality in terms of features and content. METHODS: Chatbots were identified through a systematic search on Google Play Store, Apple App Store, Alexa Skills, and the internet. An evidence-based assessment tool was used to evaluate the features and content of the identified apps. The assessment was conducted through interrater agreement among 4 separate reviewers. RESULTS: Of the 505 initial chatbots identified, 6 were included in the review. The chatbots assessed varied significantly in terms of content and scope. Although the chatbots were generally found to be easy to use, some limitations were noted regarding their performance and programmed content for dialog. CONCLUSIONS: Although chatbot technologies are well established and commonly used by the public, their development for people with dementia and their caregivers is in its infancy. Given the successful use of chatbots in other health care settings and for other applications, there are opportunities to integrate this technology into dementia care. However, more evidence-based chatbots that have undergone end user evaluation are needed to evaluate their potential to adequately educate and support these populations.

Overview

CoChat Summary

## TL;DR

This systematic review identified only 6 commercially available chatbots aimed at people with dementia and their caregivers, suggesting the field was still in an early stage. The apps were generally easy to use, but their content was limited, mostly English-only, and often not clearly evidence based.

## Key findings

  • Of 505 initial chatbots identified, only 6 met inclusion criteria; these were 1 text-based mobile app and 5 Alexa Skills voice apps.
  • Half of the apps focused on dementia education and half on memory/reminiscence; none made claims about expected outcomes, and no peer-reviewed research was identified for any of the apps.
  • In functionality, 5 of the 6 chatbots were found to be easy to use once started, and 3 of the 5 education-focused chatbots had a breadth of knowledge and flexibility in interpreting information.
  • Only 1 app passed the Turing test, and all chatbots had limited programmed dialog; 5 apps had privacy statements, and 2 apps stated they were not substitutes for medical care or advice.

## Methods

  • Systematic review and critical appraisal of commercially available chatbots for dementia, conducted between December 2019 and April 2020.
  • Searches were run on Google Play Store, Apple App Store, Amazon Alexa Skills, and the internet using terms including “Chatbot,” “Virtual Assistant,” “Alzheimer’s,” “dementia,” “health,” and “caregiver.”
  • Inclusion required interactive text or voice dialog, dementia focus, intended use by people with dementia and/or caregivers, English availability, and public availability; 4 reviewers independently assessed features/content using an evidence-based tool grounded in Radziwill and Benton, with interrater agreement and thematic analysis.

## Limitations

  • The paper states that additional dementia-related chatbots may have existed but were not identified despite an extensive search.
  • The authors note there are no standardized measurement tools for chatbot technology, and the mobile app rating scale did not fit because too many items were not applicable.
  • Evident from the text: the review assessed apps only as they existed in April/May 2020, so app characteristics may have changed afterward; also, only English-language, publicly available apps were included.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.2196/25006

Cites

42 of 42 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 Flowchart of the chatbot apps searched and the screening procedures conducted using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines.
Figure 1 Flowchart of the chatbot apps searched and the screening procedures conducted using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines.CC BY · PubMed Central

Verification

Claims the paper makes

1 Valid · 1 Not valid · 4 Not checked · 65 Own results and interpretations

28 more claims

Create a free account to see all 71 claims and every source verdict.

See all claims — free account
  • Probably not a substantial claim. 25
  • It may state two separate claims as one. 18
  • The quote only partly states this claim. 1

Create a free account to see these claims.

Citations

Cites

Show all 41 references

Research works printed but not linked: 1

  1. RadziwillNMBentonMCEvaluating quality of chatbots and intelligent conversational agentsarXiv - Computer Science, Computers and Society20172011-05-11https://arxiv.org/abs/1704.04579

Cited by

Metadata

Authors
Ruggiano, N., Brown, E. L., Roberts, L., Framil Suarez, C. V., Luo, Y., Hao, Z., & Hristidis, V.
Affiliations
  • University of Alabama (US)
  • Florida International University (US)
  • University of California, Riverside (US)
Corresponding author
Hristidis, Vagelis
Venue
Journal of Medical Internet Research
Published
2021-06-03
Volume
23
Issue
6
Pages
e25006
ISSN
1438-8871 (ISSN-L)
OpenAlex
W3164447366
Cited by
100
References
41
Citations by year
2026: 21 · 2025: 26 · 2024: 27 · 2023: 13 · 2022: 12 · 2021: 1
FWCI
2.13
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Journal of Medical Internet Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
Keywords
chatbots, dementia, family caregivers, dementia care, digital health interventions, caregiver education
MeSH terms
Delivery of Health Care, Dementia, Humans, Caregivers, Mobile Applications

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.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.