# AI-Enhanced Conversational Agents for Personalized Asthma Support in People With Asthma: Factors for Engagement, Value, and Efficacy in a Cross-Sectional Survey Study

## TL;DR

A survey of 1257 asthma patients found that 53% are interested in using a chatbot for asthma support, with preferences for 24/7 access and personalization.

## Contribution

The study identifies key factors influencing patient engagement with asthma chatbots and provides seven actionable recommendations for developers.

## Key findings

- 53% of asthma patients are interested in using a chatbot for asthma support.
- Patients with more severe asthma and lower self-management confidence are more likely to use a chatbot.
- WhatsApp is the preferred platform for chatbot access, with 24/7 availability and personalization being highly valued.

## Abstract

Asthma-related deaths in the United Kingdom are the highest in Europe, and only 30% of patients access basic care. There is a need for alternative approaches to reaching people with asthma to provide health education, self-management support, and better bridges to care.

This study aimed to examine patients’ interest in using a chatbot for asthma and to identify factors that influence engagement. Automated conversational agents (specifically, mobile chatbots) present opportunities for providing alternative and individually tailored access to health education, self-management support, and risk self-assessment. But would patients engage with a chatbot, and what factors influence engagement?

We present results from a patient survey (N=1257) developed by a team of asthma clinicians, patients, and technology developers, conducted to identify optimal factors for efficacy, value, and engagement with an asthma chatbot.

Results indicate that most adults with asthma (53%) are interested in using a chatbot. The patients most likely to do so are those who believe their asthma is more serious and are less confident in their self-management. Results also indicate enthusiasm for 24/7 access, personalization, and for WhatsApp (Meta) as the preferred access method (compared to app, voice assistant, SMS text messaging, or website).

Obstacles to uptake include security and privacy concerns and skepticism of technological capabilities. We present detailed findings and consolidate these into 7 recommendations for developers to optimize the efficacy of chatbot-based health support.