e-Health Strategy for Surgical Prioritization: A Methodology Based on Digital Twins and Reinforcement Learning

Area of Science:

• Health Informatics
• Artificial Intelligence in Medicine
• Operations Research

Background:

• Traditional elective surgery scheduling faces challenges in efficiency and equity.
• Dynamic prioritization is needed to adapt to real-time patient and system variables.
• Existing systems often lack transparency and adaptability.

Purpose of the Study:

• To present a novel methodological framework for elective surgery scheduling.
• To integrate patient-specific Digital Twins (DTs) with reinforcement learning (RL) for dynamic prioritization.
• To establish a foundation for intelligent e-health platforms supporting equitable healthcare delivery.

Main Methods:

• Developed a framework combining Digital Twins (DTs) and reinforcement learning (RL).
• Modeled clinical, economic, behavioral, and social variables for real-time prioritization scoring.
• Utilized a reinforcement learning engine to optimize patient access and maximize long-term system performance.
• Simulated surgical scheduling scenarios with synthetic patient data for validation.

Main Results:

• Achieved a 55.1% reduction in average patient wait times.
• Reduced clinical risk at the time of surgery by 41.9%.
• Increased operating room (OR) utilization by 16.1%.
• Demonstrated a significant increase in the prioritization of socially vulnerable patients.

Conclusions:

• The proposed framework offers substantial improvements over traditional surgical scheduling strategies.
• The integration of DTs and RL provides a transparent, adaptive, and ethically aligned decision-support architecture.
• This methodology serves as a valuable foundation for future smart healthcare platforms in surgical scheduling.