Provider Perspectives on Artificial Intelligence-Guided Screening for Low Ejection Fraction in Primary Care:...

Area of Science:

• Healthcare technology
• Clinical informatics
• Artificial intelligence in medicine

Background:

• Artificial intelligence (AI) offers transformative potential in healthcare but faces significant adoption barriers.
• High-accuracy AI tools, particularly for asymptomatic condition detection, may encounter resistance in clinical practice.
• Understanding healthcare providers' needs and concerns is crucial for successful AI tool implementation and adoption.

Purpose of the Study:

• To explore primary care provider perspectives on adopting an AI-enabled screening tool.
• To identify factors influencing the integration and sustained use of AI tools in primary care settings.

Main Methods:

• A qualitative study involving 29 primary care providers was conducted.
• Semistructured focus groups were used following the providers' experience with an AI tool in a pragmatic randomized controlled trial.
• Grounded theory and iterative analysis were employed to synthesize findings from focus group data.

Main Results:

• Providers recognized the AI tool's potential for accurate and rapid diagnoses.
• Successful adoption hinges on seamless integration into clinical decision-making and existing workflows, addressing provider preferences.
• Key areas for AI tool improvement include clinical decision support integration, cost-effectiveness, training, workflow alignment, care coordination, and patient communication.

Conclusions:

• Implementing AI-enabled medical tools requires sensitivity to clinical context and provider needs.
• Addressing provider perspectives is essential for the effective point-of-care adoption of AI tools in medicine.