Implementation of artificial intelligence-based decision support systems for antibiotic prescribing in hospitals: a...

Area of Science:

• Healthcare Informatics
• Artificial Intelligence in Medicine
• Clinical Decision Support

Background:

• Antimicrobial resistance (AMR) necessitates improved antibiotic stewardship.
• Artificial intelligence (AI)-based decision support systems (DSSs) offer potential for optimizing antibiotic therapy in hospitals.
• Challenges in implementing AI-based DSSs require careful consideration.

Purpose of the Study:

• To investigate factors influencing the implementation of AI-based DSSs in hospitals using a Delphi study.
• To identify key areas for successful AI-based DSS adoption in clinical settings.

Main Methods:

• A Delphi study involving 36 experts from hospital and DSS development backgrounds.
• Consensus-building on the importance and realization of 34 implementation factors.

Main Results:

• Consensus was reached on the importance of 34 factors for AI-based DSS implementation.
• Key factors for focus include user-oriented development, user-friendly structures, and establishing trust, transparency, and responsibility.
• Two factors lacked consensus on importance, suggesting a need for prioritized implementation.

Conclusions:

• Successful implementation of AI-based DSSs hinges on prioritizing user-centricity, organizational support, and ethical considerations.
• A targeted approach to implementation factors is more practical than addressing all potential issues.
• Further attention to sensitization and education is crucial for organizational and legal acceptance.