JMIR Publications

ABSTRACT

Background:

Personalization of the conversational agents (CA) with natural language user interfaces is increasingly used in healthcare applications, shaping the content, structure or purpose of the dialogue between human and CA.

Objective:

To understand the ways in which personalization has been used with conversational agents in healthcare and characterize the methods to implement personalization.

Methods:

We searched on PubMed, Embase, CINAHL, PsycInfo, and ACM Digital Library using a predefined search strategy. The studies were included if they i) were primary research studies that focused on consumers, caregivers, or healthcare professionals; ii) involved a conversational agent with an unconstrained natural language interface; iii) tested the system with human subjects; and iv) 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 personalization and with limited evaluation of the impact of personalization. While conversational agents with personalization features were reported to improve user satisfaction, user engagement and dialog quality, the role of personalization in improving health outcomes was not assessed directly.

Conclusions:

Most of the studies in our review were implementations of basic personalization methods, lagging behind the advances in the recent studies of personalization in other domains. Future research can i) adopt formal methods and theories of personalization and ii) incorporate personalization as a distinct design factor with a more careful consideration of its role in supporting health outcomes and its implications on patient safety, privacy, and decision-making.