Self-Diagnosis through AI-enabled Chatbot-based Symptom Checkers: User Experiences and Design Considerations

TL;DR

This study reviews AI chatbot symptom checkers, revealing gaps in functionality and user experience, and suggests improvements for more comprehensive and user-friendly healthcare self-diagnosis tools.

Contribution

It provides a detailed analysis of current CSC apps' features and user perceptions, offering design implications to enhance their diagnostic support capabilities.

Findings

Current CSC apps lack support for full diagnostic processes.

Users find existing apps insufficient for comprehensive medical history.

Design suggestions for improved symptom input and question clarity.

Abstract

Recently, there has been a growing interest in developing AI-enabled chatbot-based symptom checker (CSC) apps in the healthcare market. CSC apps provide potential diagnoses for users and assist them with self-triaging based on Artificial Intelligence (AI) techniques using human-like conversations. Despite the popularity of such CSC apps, little research has been done to investigate their functionalities and user experiences. To do so, we conducted a feature review, a user review analysis, and an interview study. We found that the existing CSC apps lack the functions to support the whole diagnostic process of an offline medical visit. We also found that users perceive the current CSC apps to lack support for a comprehensive medical history, flexible symptom input, comprehensible questions, and diverse diseases and user groups. Based on these results, we derived implications for the future features and conversational design of CSC apps.