Dynamic surgical prioritization: a machine learning and XAI-based strategy

Silva-Aravena, F, Morales, J, Jayabalan, M ORCID: 0000-0002-1599-965X, Rana, M.E and Gutiérrez-Bahamondes, J.H (2025) 'Dynamic surgical prioritization: a machine learning and XAI-based strategy.' Technologies, 13 (2). e72.

Preview

Text 17218.pdf - Published Version CC BY 4.0. Download (676kB) | Preview

Abstract

Surgical waiting lists present significant challenges to healthcare systems, particularly in resource-constrained settings where equitable prioritization and efficient resource allocation are critical. We aim to address these issues by developing a novel, dynamic, and interpretable framework for prioritizing surgical patients. Our methodology integrates machine learning (ML), stochastic simulations, and explainable AI (XAI) to capture the temporal evolution of dynamic prioritization scores, qp(t), while ensuring transparency in decision making. Specifically, we employ the Light Gradient Boosting Machine (LightGBM) for predictive modeling, stochastic simulations to account for dynamic variables and competitive interactions, and SHapley Additive Explanations (SHAPs) to interpret model outputs at both the global and patient-specific levels. Our hybrid approach demonstrates strong predictive performance using a dataset of 205 patients from an otorhinolaryngology (ENT) unit of a high-complexity hospital in Chile. The LightGBM model achieved a mean squared error (MSE) of 0.00018 and a coefficient of determination (R2) value of 0.96282, underscoring its high accuracy in estimating qp(t). Stochastic simulations effectively captured temporal changes, illustrating that Patient 1’s qp(t) increased from 0.50 (at t=0) to 1.026 (at t=10) due to the significant growth of dynamic variables such as severity and urgency. SHAP analyses identified severity (Sever) as the most influential variable, contributing substantially to qp(t), while non-clinical factors, such as the capacity to participate in family activities (Lfam), exerted a moderating influence. Additionally, our methodology achieves a reduction in waiting times by up to 26%, demonstrating its effectiveness in optimizing surgical prioritization. Finally, our strategy effectively combines adaptability and interpretability, ensuring dynamic and transparent prioritization that aligns with evolving patient needs and resource constraints.

Item Type:	Article
Keywords:	dynamic prioritization, machine learning in healthcare, explainable AI, surgical waiting lists, stochastic simulation
Divisions:	Bath School of Design
Date Deposited:	22 Aug 2025 14:15
Last Modified:	22 Aug 2025 14:15
ISSN:	2227-7080
URN:	https://researchspace.bathspa.ac.uk/id/eprint/17218

	Request a change to this item or report an issue
	Update item (repository staff only)