Conversational Agents for Asthma and Chronic Obstructive Pulmonary Disease Management: Scoping Review

Abstract

Abstract Background Asthma and chronic obstructive pulmonary disease (COPD) affect more than 650 million people worldwide and remain leading causes of disability, with a rising burden as populations age. Conversational agents (CAs) may offer a more interactive alternative. However, the evidence in obstructive lung disease has not been mapped. Objective The aim of this study is to map the literature on CA use in asthma and COPD, to describe the roles they have been designed to perform, the outcomes that have been measured, and to map the study designs and methods characterizing the current evidence. Methods A scoping review was conducted following the Arksey and O’Malley framework. A total of 9 databases (CINAHL, CENTRAL, Embase, IEEE Xplore, PubMed, ProQuest, Scopus, Web of Science, and Google Scholar) were searched from January 1, 2014, to February 22, 2025. Data were synthesized using inductive content analysis and organized via the Patterns, Advances, Gaps, Evidence for Practice, and Research Recommendations (PAGER) framework. Reporting followed PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. Results A total of 6275 records were screened, and 16 reports from 15 studies were included. Studies reported CAs being used for information provision and patient education, health data collection, and emotional or motivational support. Only 4 studies measured direct clinical outcomes (eg, asthma control or medication adherence). Reported usability and satisfaction findings were mixed, with recurring concerns about conversational flow, responsiveness, trust, and personalization. Conclusions The evidence base for CAs in asthma and COPD remains in early developmental stages. It consists mainly of small feasibility, developmental, and pilot studies, providing limited evidence on whether CAs improve clinical outcomes. Current evidence can mainly describe the roles CAs have been designed to perform and the user-experience factors that influence engagement. Adequately powered, longitudinal trials using clinically meaningful and standardized endpoints are required before effectiveness can be assessed. Future development should place patients, as the end users, at the center of co-design, with clinicians, including nurses, involved to ensure clinical relevance and safe integration into care.

The authors' abstract, as published at the source. Journal of Medical Internet Research, 2026 · DOI ↗