Evaluation framework for conversational agents with artificial intelligence in health interventions: a systematic scoping review

Key Points

• The central aim is to establish an evaluation framework for AI-powered conversational agents used in health interventions.
• Conducted a systematic scoping review
• Analyzed various AI conversational agents in health applications
• Identified key evaluation criteria and frameworks
• Progress in assessing effectiveness and user satisfaction of AI conversational agents noted
• Highlighted best practices and gaps in current evaluation methods
• Recommendations for future research on evaluation frameworks provided