LLM-Enhanced, Data-Driven Personalized and Equitable Clinician Scheduling: A Predict-then-Optimize Approach

2025-10-02

AI Summary

Clinical physician scheduling faces challenges including limited resources, fluctuating demand, multi-site coordination, and complex individual preferences. Conventional rule- or statistics-based optimization methods fail to exploit implicit availability and constraint information embedded in unstructured text—such as well-being survey responses and free-text inputs from scheduling platforms. This paper proposes the first prediction–optimization framework integrating large language models (LLMs) with mixed-integer programming (MIP). The LLM is employed for the first time to parse scheduling-related free text, automatically extracting physicians’ latent preferences and soft constraints. The MIP component formulates a multi-objective model balancing fairness, regulatory compliance, workload equity, and resource utilization. Experimental results demonstrate significant improvements in shift matching accuracy and schedule consistency, reduced burnout risk, and the unlocking of previously unrecognized workforce flexibility.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Clinician scheduling remains a persistent challenge due to limited clinical resources and fluctuating demands. This complexity is especially acute in large academic anesthesiology departments as physicians balance responsibilities across multiple clinical sites with conflicting priorities. Further, scheduling must account for individual clinical and lifestyle preferences to ensure job satisfaction and well-being. Traditional approaches, often based on statistical or rule-based optimization models, rely on structured data and explicit domain knowledge. However, these methods often overlook unstructured information, e.g., free-text notes from routinely administered clinician well-being surveys and scheduling platforms. These notes may reveal implicit and underutilized clinical resources. Neglecting such information can lead to misaligned schedules, increased burnout, overlooked staffing flexibility, and suboptimal utilization of available resources. To address this gap, we propose a predict-then-optimize framework that integrates classification-based clinician availability predictions with a mixed-integer programming schedule optimization model. Large language models (LLMs) are employed to extract actionable preferences and implicit constraints from unstructured schedule notes, enhancing the reliability of availability predictions. These predictions then inform the schedule optimization considering four objectives: first, ensuring clinical full-time equivalent compliance, second, reducing workload imbalances by enforcing equitable proportions of shift types, third, maximizing clinician availability for assigned shifts, and fourth, schedule consistency. By combining the interpretive power of LLMs with the rigor of mathematical optimization, our framework provides a robust, data-driven solution that enhances operational efficiency while supporting equity and clinician well-being.

Problem

• Improving clinician scheduling using LLMs to extract preferences from unstructured notes
• Addressing workload imbalances and ensuring equitable shift distribution among clinicians
• Optimizing resource utilization while supporting clinician well-being and job satisfaction

Innovation

• LLMs extract preferences from unstructured text notes
• Predict-then-optimize combines classification with MIP scheduling
• Balances four objectives including equity and clinician availability