CoChat

Voice-Based Conversational Agents for the Prevention and Management of Chronic and Mental Health Conditions: Systematic Literature Review

Open access
Bérubé, Caterina, Schachner, Theresa, Keller, Roman, Fleisch, Elgar, v Wangenheim, Florian, Barata, Filipe, Kowatsch, Tobias · 2021 · Journal of Medical Internet Research

Published version of a preprint

The DOI matches its Crossref record; 75 of the 75 references it cites were found in a registry or an index; 129 of the 325 sources its claims cite were checked for support.

Abstract

BACKGROUND: Chronic and mental health conditions are increasingly prevalent worldwide. As devices in our everyday lives offer more and more voice-based self-service, voice-based conversational agents (VCAs) have the potential to support the prevention and management of these conditions in a scalable manner. However, evidence on VCAs dedicated to the prevention and management of chronic and mental health conditions is unclear. OBJECTIVE: This study provides a better understanding of the current methods used in the evaluation of health interventions for the prevention and management of chronic and mental health conditions delivered through VCAs. METHODS: We conducted a systematic literature review using PubMed MEDLINE, Embase, PsycINFO, Scopus, and Web of Science databases. We included primary research involving the prevention or management of chronic or mental health conditions through a VCA and reporting an empirical evaluation of the system either in terms of system accuracy, technology acceptance, or both. A total of 2 independent reviewers conducted the screening and data extraction, and agreement between them was measured using Cohen kappa. A narrative approach was used to synthesize the selected records. RESULTS: Of 7170 prescreened papers, 12 met the inclusion criteria. All studies were nonexperimental. The VCAs provided behavioral support (n=5), health monitoring services (n=3), or both (n=4). The interventions were delivered via smartphones (n=5), tablets (n=2), or smart speakers (n=3). In 2 cases, no device was specified. A total of 3 VCAs targeted cancer, whereas 2 VCAs targeted diabetes and heart failure. The other VCAs targeted hearing impairment, asthma, Parkinson disease, dementia, autism, intellectual disability, and depression. The majority of the studies (n=7) assessed technology acceptance, but only few studies (n=3) used validated instruments. Half of the studies (n=6) reported either performance measures on speech recognition or on the ability of VCAs to respond to health-related queries. Only a minority of the studies (n=2) reported behavioral measures or a measure of attitudes toward intervention-targeted health behavior. Moreover, only a minority of studies (n=4) reported controlling for participants' previous experience with technology. Finally, risk bias varied markedly. CONCLUSIONS: The heterogeneity in the methods, the limited number of studies identified, and the high risk of bias show that research on VCAs for chronic and mental health conditions is still in its infancy. Although the results of system accuracy and technology acceptance are encouraging, there is still a need to establish more conclusive evidence on the efficacy of VCAs for the prevention and management of chronic and mental health conditions, both in absolute terms and in comparison with standard health care.

Overview

CoChat Summary

## TL;DR

This systematic review identified 12 studies on voice-based conversational agents (VCAs) for chronic and mental health conditions out of 7170 prescreened papers, and found that the evidence is still preliminary. The studies were all nonexperimental, highly heterogeneous, and generally focused on technology acceptance and system accuracy rather than actual clinical effectiveness.

## Key findings

  • Of 7170 prescreened papers, 12 met the inclusion criteria; all 12 studies were nonexperimental.
  • VCAs were used for behavioral support (n=5), health monitoring (n=3), or both (n=4), and were delivered via smartphones (n=5), tablets (n=2), smart speakers (n=3), or unspecified devices (n=2).
  • Technology acceptance was assessed in 7 studies, but only 3 used validated instruments; system performance was reported in 6 studies, with 3 describing good or very good speech recognition performance and 1 reporting mediocre recognition accuracy.
  • The included studies targeted a range of conditions, including cancer (n=3 VCAs), diabetes (n=2), heart failure (n=2), hearing impairment, asthma, Parkinson disease, dementia, autism, intellectual disability, and depression.
  • Risk bias varied markedly, with scores ranging from 1 to 11.25 and a median of 6.36.

## Methods

  • Systematic literature review following PRISMA, searching PubMed MEDLINE, Embase, PsycINFO, Scopus, and Web of Science; the search was conducted using literature available in July 2020.
  • Included primary research on prevention, treatment, or management of chronic diseases or mental disorders delivered through a voice-based conversational agent, with empirical evaluation of system accuracy and/or technology acceptance.
  • Two independent reviewers screened titles, abstracts, and full texts; two reviewers extracted data; disagreement was resolved with a third investigator; synthesis was narrative, and risk of bias was assessed using an adapted CONSORT-based tool.

## Limitations

  • The paper states that its search strategy used nonspecific terms such as “health,” which may have retrieved many irrelevant papers; this was an explicit tradeoff to avoid missing relevant literature.
  • The review covers research evidence only and does not include industry developments; this is stated in the paper.
  • The authors state that their bias tool may be unsuitable because none of the included papers were experimental trials; this is a limitation stated in the paper.
  • Evident from the text: the evidence base is small (12 studies), all studies were nonexperimental and mostly laboratory/short-term evaluations, so the review cannot establish actual effectiveness of VCAs in improving health outcomes.

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

Integrity signals

Registry

Crossref · 10.2196/25933

Cites

75 of 75 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) flow diagram of included studies.
Figure 1 PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) flow diagram of included studies.CC BY · PubMed Central

Verification

Claims the paper makes

53 Valid · 6 Not valid · 39 Not checked · 73 Own results and interpretations

49 more claims · 12 with their cited sources checked

Create a free account to see all 171 claims and every source verdict.

See all claims — free account
  • Probably not a substantial claim. 69
  • It may state two separate claims as one. 79
  • The quote only partly states this claim. 1

Create a free account to see these claims.

Citations

Cites

Research works printed but not linked: 7

  1. 2020, World Health Statistics 2020: monitoring health for the SDGs, sustainable development goals, 1
  2. 2019, Document number: WHO/MSD/MER/19.3
  3. 10.1136/bmj.g7647 · DOI · Paper page
  4. Amith, M, 2019, Stud Health Technol Inform, 257, 17
  5. Amith, M, 2020, AMIA Jt Summits Transl Sci Proc, 2020, 43
  6. Ireland, D, 2016, Stud Health Technol Inform, 227, 55
  7. Moorthy, AE, 2014, Information and Knowledge in Applications and Services, 324

Cited by

See all 133

Metadata

Authors
Bérubé, C., Schachner, T., Keller, R., Fleisch, E., v Wangenheim, F., Barata, F., & Kowatsch, T.
Affiliations
  • ETH Zurich (CH)
  • Singapore-ETH Centre (SG)
  • University of St.Gallen (CH)
  • National University of Singapore (SG)
Corresponding author
Bérubé, Caterina
Venue
Journal of Medical Internet Research
Published
2021-03-29
Volume
23
Issue
3
Pages
e25933
ISSN
1438-8871 (ISSN-L)
OpenAlex
W3135619344
Cited by
133
References
74
Citations by year
2026: 22 · 2025: 33 · 2024: 34 · 2023: 15 · 2022: 18 · 2021: 11
FWCI
3.13
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)
  • Repository for Publications and Research Data (ETH Zurich) (submittedVersion, cc-by)
  • National University of Singapore (submittedVersion, cc-by)
  • Alexandria (UniSG) (University of St.Gallen) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • ETH Zürich Research Collection (cc-by)
Funders
National Research Foundation
Topics
  • Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
  • Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Telemedicine and Telehealth Implementation
Keywords
voice assistants, chronic disease prevention, mental health, health behavior change, technology acceptance, speech recognition accuracy, health monitoring, behavioral support, health intervention evaluation, risk of bias, cancer, diabetes mellitus, heart failure, depression, dementia, autism spectrum disorder, hearing loss, Parkinson's disease, asthma, intellectual disability, smart speakers, smartphones, tablets, risk of bias assessment tools
MeSH terms
Smartphone, Asthma, Communication, Humans, Mental Health, Health Behavior

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

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.