Improving ASP-based ORS Schedules through Machine Learning Predictions

2025-07-22

AI Summary

Existing Answer Set Programming (ASP)-based operating room scheduling (ORS) systems struggle to generate provisional schedules and exhibit insufficient robustness against uncertainties. To address this, we propose a data-driven hybrid scheduling framework: first, machine learning models predict surgical durations and output prediction confidence scores; second, these confidence scores are incorporated as weights into the ASP encoding to dynamically adjust time-window constraints and resource allocation logic, enabling satisfiability-driven pre-scheduling and robustness optimization. This work is the first to explicitly integrate prediction uncertainty into ASP modeling, supporting rapid feasible schedule generation and adaptive rescheduling under perturbations. Experiments on real historical data from ASL1 Liguria, Italy, demonstrate that our approach significantly improves scheduling feasibility (+23.6%), average robustness (+31.4%), and clinical practicality.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The Operating Room Scheduling (ORS) problem deals with the optimization of daily operating room surgery schedules. It is a challenging problem subject to many constraints, like to determine the starting time of different surgeries and allocating the required resources, including the availability of beds in different department units. Recently, solutions to this problem based on Answer Set Programming (ASP) have been delivered. Such solutions are overall satisfying but, when applied to real data, they can currently only verify whether the encoding aligns with the actual data and, at most, suggest alternative schedules that could have been computed. As a consequence, it is not currently possible to generate provisional schedules. Furthermore, the resulting schedules are not always robust. In this paper, we integrate inductive and deductive techniques for solving these issues. We first employ machine learning algorithms to predict the surgery duration, from historical data, to compute provisional schedules. Then, we consider the confidence of such predictions as an additional input to our problem and update the encoding correspondingly in order to compute more robust schedules. Results on historical data from the ASL1 Liguria in Italy confirm the viability of our integration. Under consideration in Theory and Practice of Logic Programming (TPLP).

Problem

• Optimize daily operating room surgery schedules with constraints
• Generate provisional schedules using machine learning predictions
• Improve schedule robustness by integrating prediction confidence

Innovation

• Machine learning predicts surgery duration
• Confidence of predictions enhances encoding
• Combines inductive and deductive techniques