CoChat

The Personalization of Conversational Agents in Health Care: Systematic Review

Open access

Published version of a preprint

The DOI matches its Crossref record; 64 of the 65 references it cites were found in a registry or an index; 8 of the 18 sources its claims cite were checked for support.

Abstract

BACKGROUND: The personalization of conversational agents with natural language user interfaces is seeing increasing use in health care applications, shaping the content, structure, or purpose of the dialogue between humans and conversational agents. OBJECTIVE: The goal of this systematic review was to understand the ways in which personalization has been used with conversational agents in health care and characterize the methods of its implementation. METHODS: We searched on PubMed, Embase, CINAHL, PsycInfo, and ACM Digital Library using a predefined search strategy. The studies were included if they: (1) were primary research studies that focused on consumers, caregivers, or health care professionals; (2) involved a conversational agent with an unconstrained natural language interface; (3) tested the system with human subjects; and (4) implemented personalization features. RESULTS: The search found 1958 publications. After abstract and full-text screening, 13 studies were included in the review. Common examples of personalized content included feedback, daily health reports, alerts, warnings, and recommendations. The personalization features were implemented without a theoretical framework of customization and with limited evaluation of its impact. While conversational agents with personalization features were reported to improve user satisfaction, user engagement and dialogue quality, the role of personalization in improving health outcomes was not assessed directly. CONCLUSIONS: Most of the studies in our review implemented the personalization features without theoretical or evidence-based support for them and did not leverage the recent developments in other domains of personalization. Future research could incorporate personalization as a distinct design factor with a more careful consideration of its impact on health outcomes and its implications on patient safety, privacy, and decision-making.

Overview

CoChat Summary

## TL;DR

This systematic review found only 13 health care conversational-agent studies with personalization features, and most personalized content rather than conversational style. The paper concludes that personalization was rarely theory-based or directly evaluated for health outcomes.

## Key findings

  • The search identified 1958 publications in total; after screening, 13 studies were included.
  • Personalization was most often used for content delivery: feedback, daily health reports, alerts, warnings, recommendations, reminders, multimedia, and personalized questions.
  • Across the 13 studies, 8 supported patients and 5 supported both patients and clinicians; all used individuated personalization, and 1 study also used categorical personalization for novice vs expert users.
  • Only 2 studies directly assessed personalization itself; one reported that 85% (29/34) found tailored feedback helpful, and another rated customized feedback 0.3 on a –2 to +2 Likert scale as the most successful feature.

## Methods

  • Systematic review of health care conversational agents with unconstrained natural language input and personalization features.
  • Searched PubMed, Embase, CINAHL, PsycInfo, and ACM Digital Library in March 2019, with no publication-year or language restriction.
  • Included primary studies on consumers, caregivers, or health care professionals that tested a conversational agent with human users and implemented personalization; screening/data extraction were done independently by two researchers, with Cohen kappa used for agreement.

## Limitations

  • The authors state the results are limited by how much the included studies reported their personalization features.
  • The review focused only on CAs with unconstrained natural language input, so the findings may not extend to constrained systems; this is stated in the paper.
  • Evident from the text: outcomes in the included studies were often attributable to the overall system rather than personalization alone, making it hard to isolate personalization effects.

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

Integrity signals

Registry

Crossref · 10.2196/15360

Cites

64 of 64 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 Preferred Reporting Items for Systematic Reviews and Meta-Analyses flow diagram.
Figure 1 Preferred Reporting Items for Systematic Reviews and Meta-Analyses flow diagram.CC BY · PubMed Central

Verification

Claims the paper makes

5 Valid · 0 Not valid · 6 Not checked · 32 Own results and interpretations

26 more claims

Create a free account to see all 43 claims and to verify the 1 reference still open.

See all claims — free account
  • It may state two separate claims as one. 6
  • Probably not a substantial claim. 6

Create a free account to see these claims.

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?

4 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Citations

Cites

Show all 64 references

Research works printed but not linked: 8

  1. Cambridge dictionaries online20152019-09-16Cambridge University Presshttp://dictionary.cambridge.org
  2. Coiera, E, 2012, Yearb Med Inform, 7, 4
  3. Radziwill, NM, 2017, arXiv preprint, 1
  4. 10.2196/jmir.8.4.e30 · DOI · Paper page
  5. Azzini, I, 2003, Stud Health Technol Inform, 95, 146
  6. Chu-CarrollJNickersonJSEvaluating automatic dialogue strategy adaptation for a spoken dialogue system2000North American Chapter of the Association for Computational Linguistics ConferenceApril 29 - May 04, 2000Seattle, WashingtonAssociation for Computational Linguistics202209
  7. Carr, N, 2015, The glass cage: Where automation is taking us
  8. 10.1007/s10916-019-1237-1 · DOI · Paper page

Cited by

Items 201–300 of 325

Metadata

Authors
Kocaballi, A. B., Berkovsky, S., Quiroz, J. C., Laranjo, L., Tong, H. L., Rezazadegan, D., Briatore, A., & Coiera, E.
Affiliations
  • Macquarie University (AU)
  • Ministerio de Salud (AR)
Corresponding author
Kocaballi, Ahmet Baki
Venue
Journal of Medical Internet Research
Published
2019-11-07
Volume
21
Issue
11
Pages
e15360
ISSN
1438-8871 (ISSN-L)
OpenAlex
W2972203331
Cited by
332
References
65
Citations by year
2026: 57 · 2025: 64 · 2024: 47 · 2023: 56 · 2022: 38 · 2021: 48 · 2020: 21 · 2019: 1
FWCI
1.30
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)
  • Swinburne figshare (Swinburne University of Technology) (submittedVersion, other-oa)
  • Greater South Information System
Funders
  • Directorate for Computer and Information Science and Engineering
  • Medical Research Council
  • National Health and Medical Research Council (1134919)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
Keywords
chatbots, personalization, health care, natural language interfaces, personalized feedback, user satisfaction, user engagement, dialogue quality, patient safety, privacy, decision support
MeSH terms
Delivery of Health Care, Humans, Precision Medicine

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 2026-10-10, 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).

Cited sources are checked with a language model’s help (qwen3.8-omni-flash and 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.