Achieving SDoH Resource Equity in PICU Using an AI-Enabled Patient Navigator

Area of Science:

• Pediatric critical care medicine
• Health informatics
• Artificial intelligence in healthcare

Background:

• Trauma care coordination in pediatric intensive care units (PICUs) is complex, particularly when personalizing resources based on social determinants of health (SDoH).
• Inconsistent and fragmented SDoH data collection during hospitalization hinders effective resource allocation and usability for patients and healthcare providers.
• Existing systems strain healthcare providers, necessitating innovative solutions for efficient patient care.

Purpose of the Study:

• To propose the implementation of artificial intelligence (AI) tools to standardize SDoH data collection in the PICU.
• To enhance resource navigation for patients and providers during and after trauma hospitalization.
• To improve the overall efficiency and effectiveness of trauma care coordination.

Main Methods:

• Implementing AI tools for standardized SDoH data collection.
• Utilizing the RE-AIM Framework for evaluation.
• Assessing tool and process reach, effectiveness, adoption, implementation, and maintenance.

Main Results:

• The study aims to evaluate the reach and effectiveness of AI tools for SDoH data standardization.
• User-friendliness of the AI tools and the overall process will be assessed.
• The percentage of resource allocation and utilization will be measured to determine impact.

Conclusions:

• AI tools offer a promising solution for standardizing SDoH data in PICUs.
• Enhanced resource navigation can improve patient and provider experiences in trauma care.
• The RE-AIM Framework provides a robust method for evaluating the implementation of these AI solutions.