Interactive Conversational Agents to Improve Dietary Behaviors for Health Promotion: Mixed Systematic Review

Area of Science:

• Digital health interventions
• Behavioral science
• Public health

Background:

• Chronic diseases are a leading cause of death, driven by lifestyle factors like poor diet and inactivity.
• Digital interventions, particularly conversational agents (CAs), offer personalized support for health behavior change.
• Limited evidence exists on the effectiveness of CAs for improving dietary behaviors and preventing chronic diseases.

Purpose of the Study:

• To evaluate the effectiveness of CAs in improving dietary behaviors.
• To describe CA features, functions, and conversational capabilities.
• To assess CA impact on nutritional knowledge, usability, acceptability, user experience, and engagement.

Main Methods:

• Systematic review of 5 databases (MEDLINE, CINAHL, Embase, Web of Science, PsycINFO) for studies since 2013.
• Included studies focused on CA use for dietary behavior change; assessed using the Mixed Methods Appraisal Tool.
• Narrative synthesis of quantitative and qualitative findings from 10 studies.

Main Results:

• Improvements in fruit/vegetable intake and Mediterranean diet adherence were observed.
• Enhanced nutritional knowledge was reported; effects on other dietary components were mixed.
• Modest weight loss and increased physical activity were noted in some studies; usability was generally positive.

Conclusions:

• Conversational agents demonstrate promise for improving dietary behaviors and supporting weight management.
• Variability in outcomes, attrition, and limited social support highlight areas for improvement.
• Future research should focus on larger samples, longer follow-up, and enhanced engagement strategies for chronic disease prevention.