Data Transformation to Advance AI/ML Research and Implementation in Primary Care.

Area of Science:

• Health Informatics
• Artificial Intelligence in Medicine
• Primary Care Research

Background:

• Artificial intelligence and machine learning (AI/ML) are rapidly advancing in healthcare.
• Primary care, as a major health delivery platform, is poised for significant AI/ML impact.
• A critical barrier to AI/ML adoption in primary care is the lack of organized, large-scale datasets.

Purpose of the Study:

• To propose key considerations for data transformation to facilitate AI/ML growth in primary care.
• To outline strategies for overcoming data challenges in primary care research and development.
• To highlight the potential of primary care data to drive AI/ML advancements in healthcare.

Main Methods:

• The article outlines high-level considerations for data transformation.
• Focuses on automating data collection and organizing fragmented data.
• Emphasizes identifying primary care-specific use cases and integrating AI/ML into clinical workflows.

Main Results:

• Identifies critical data transformation needs for AI/ML in primary care.
• Proposes a framework for data collection, organization, and integration.
• Suggests the need for surveillance of unintended consequences of AI/ML implementation.

Conclusions:

• Primary care holds immense potential for AI/ML advancement.
• Data transformation is essential to unlock AI/ML's benefits for patients and clinicians.
• Strategic data utilization can position primary care at the forefront of healthcare AI/ML innovation.