Journal of the Operational Research Society

Operational Research and Artificial Intelligence for Transforming Healthcare

Healthcare services worldwide face sustained pressure from ageing populations, workforce shortages, rising demand, and constrained budgets. At the same time, the rapid growth of digital health data and advances in artificial intelligence are creating unprecedented opportunities to redesign how care is planned, delivered, and evaluated. Operational Research (OR) has a long tradition of supporting healthcare decision-making (Petropoulos et al., 2024), and its integration with AI and machine learning methods is now opening new frontiers in modelling, optimisation, and decision support.

The recent JORS special issue on Operational Research and Generative AI (Choi et al., 2026) demonstrated the breadth and vitality of the OR–AI interface, with a focus specifically on generative AI. Building on that foundation, the present special issue focuses on healthcare, a domain where trustworthy and verifiable AI is an urgent research priority. It encompasses the full spectrum of artificial intelligence methods, from machine learning and reinforcement learning to large language models and generative approaches, and their interface with OR.

The special issue invites high-quality original research at the interface of Operational Research and Artificial Intelligence in health and healthcare, including methodological contributions, applied studies with demonstrable practical impact, and papers addressing implementation and evaluation in real healthcare settings. Submissions should make a substantive contribution at the OR–AI interface; manuscripts centred primarily on optimisation, simulation methodology, or on health services research without a significant AI component, may be better suited to other journals in the OR Society portfolio.

Methods of interest include, but are not limited to:

• Machine learning and predictive modelling for patient flow, demand forecasting, and clinical decision support integrated with OR
• Large language models, generative AI, and retrieval-augmented generation, including the extraction of modelling insight from unstructured clinical documents and health records, as input for OR models
• Reinforcement learning and approximate dynamic programming for sequential decisions in screening, treatment, and care planning
• Generative approaches to synthetic health data for modelling and privacy-preserving analysis and their support for OR methods.
• Optimisation of healthcare resources, including workforce planning, scheduling, and capacity management, using AI and OR integrated methodologies.
• Hybrid simulation–AI approaches for the design and evaluation of care delivery
• Data-driven and digital-twin models of care pathways and healthcare delivery
• Statistical and stochastic modelling of patient journeys and survival

Themes and applications:

• AI-enhanced planning and delivery of care: emergency and unscheduled care, elective recovery, workforce, and community care
• Personalised and stratified care: AI-enabled pathways, screening and prevention, and chronic disease management
• Human–AI collaboration in clinical and operational decision-making
• Trustworthy AI in health: equity, ethics, transparency, and verification of AI-informed decisions
• Implementation and evaluation: translating OR/AI models into healthcare practice

References

Choi, T.-M., Basu, P., Tiwari, S., Biswas, I., & Kunc, M. (2026). Exploring complementarities and differences between Operational Research and Generative AI to transform operations. Journal of the Operational Research Society, 77(7), 1665–1674. https://doi.org/10.1080/01605682.2026.2674225

Petropoulos, F., Laporte, G., Aktas, E., Alumur, S. A., Archetti, C., Ayhan, H., … Zhao, X. (2024). Operational Research: methods and applications. Journal of the Operational Research Society, 75(3), 423–617. https://doi.org/10.1080/01605682.2023.2253852