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

Abstract

This article presents a methodological framework for elective surgery scheduling based on the integration of patient-specific Digital Twins (DTs) and reinforcement learning (RL). The proposed approach aims to support the future development of an intelligent e-health platform for dynamic, data-driven prioritization of surgical patients. We generate prioritization scores by modeling clinical, economic, behavioral, and social variables in real time and optimize access through a reinforcement learning engine designed to maximize long-term system performance. The methodology is designed as a modular, transparent, and interoperable digital decision-support architecture aligned with the goals of organizational transformation and equitable healthcare delivery. To validate its potential, we simulate realistic surgical scheduling scenarios using synthetic patient data. Results demonstrate substantial improvements compared withto traditional strategies, including a 55.1% reduction in average wait time, a 41.9% decrease in clinical risk at surgery, a 16.1% increase in OR utilization, and a significant increase in the prioritization of socially vulnerable patients. These findings highlight the value of the proposed framework as a foundation for future smart healthcare platforms that support transparent, adaptive, and ethically aligned decision-making in surgical scheduling.

Keywords: Digital Twin; digital decision support; e-Health platform; equitable access; intelligent scheduling; reinforcement learning.

Figure 1

Conceptual architecture of the proposed methodology, illustrating the integration of the Patient Interface, Clinical Dashboard, Digital Twins, RL-based Decision Engine, and Data Lake. Arrows represent the dynamic flow of information and feedback within the envisioned e-health ecosystem.

Figure 2

Distribution of patient wait times across models. The RL + DT model shows both a lower median and reduced variability. The outlier is shown as a single point.

Figure 3

Distribution of clinical risk at the time of surgery across models. RL + DT reduces both the average and the variability of risk scores. Outliers are displayed as individual points.

Figure 4

Simulated distribution of OR utilization efficiency by scheduling model. The RL + DT model achieves higher and more stable efficiency. Outliers are displayed as individual points.

Figure 5

Simulated distribution of vulnerable patients scheduled weekly under different models. The RL + DT model achieves the highest and most consistent equity performance.