Artificial intelligence-enhanced care pathway planning and scheduling system: content validity assessment of required...

Area of Science:

• Healthcare Informatics
• Artificial Intelligence in Medicine
• Clinical Workflow Optimization

Background:

• Artificial intelligence (AI) and machine learning (ML) are revolutionizing healthcare workflows.
• A need exists for defined clinical requirements for AI-enhanced systems to improve human-AI interaction.
• This study aimed to assess content validity and prioritize functionalities for AI-driven care pathway planning and scheduling.

Purpose of the Study:

• Assess content validity of AI functionalities for care pathway planning.
• Prioritize essential features for AI-enhanced healthcare systems.
• Guide the development of effective human-AI collaboration in clinical settings.

Main Methods:

• Prospective content validity assessment across five university hospitals in three countries.
• Electronic survey utilizing generic statements of required AI functionalities.
• Content validity index and weighted ranking points used for evaluation and prioritization.

Main Results:

• 50 clinical professionals provided input, with item-level content validity indices ranging from 0.42 to 0.96.
• Top-ranked functionalities included risk assessment, patient profiling, and resource management.
• Explainability of machine learning models was a highly prioritized user interface feature.

Conclusions:

• A comprehensive list of functionalities for designing and evaluating AI-enhanced healthcare solutions was generated.
• The perceived relevance of AI functionalities may be influenced by organizational readiness for AI adoption in healthcare.
• Findings provide a foundation for developing more effective AI tools in clinical practice.