Assortment Optimization for Patient-Provider Matching

2025-02-14

AI Summary

High provider turnover in healthcare systems necessitates frequent patient–provider re-matching, undermining continuity of care and system efficiency. Method: We propose a “menu-based” joint matching paradigm wherein each patient receives a personalized subset of providers (a “menu”) and autonomously selects their preferred match, balancing systemic efficiency with individual preferences. This is the first work to formulate the problem as a combinatorial optimization task, integrating stochastic choice modeling with empirically grounded strategy analysis. Contribution/Results: We identify strong sensitivity of matching performance to patient preference strength and the provider-to-patient supply-demand ratio. We further devise a patient-feature-adaptive menu-sizing strategy. Evaluated on real-world healthcare data, our approach improves matching quality by 13% over greedy baselines, demonstrating significant gains in both fairness and utility. The framework yields actionable, implementation-ready system design guidelines for health IT platforms.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Learning Preferences or Rankings
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Rising provider turnover forces healthcare administrators to frequently rematch patients to available providers, which can be cumbersome and labor-intensive. To reduce the burden of rematching, we study algorithms for matching patients and providers through assortment optimization. We develop a patient-provider matching model in which we simultaneously offer each patient a menu of providers, and patients subsequently respond and select providers. By offering assortments upfront, administrators can balance logistical ease and patient autonomy. We study policies for assortment optimization and characterize their performance under different problem settings. We demonstrate that the selection of assortment policy is highly dependent on problem specifics and, in particular, on a patient's willingness to match and the ratio between patients and providers. On real-world data, we show that our best policy can improve match quality by 13% over a greedy solution by tailoring assortment sizes based on patient characteristics. We conclude with recommendations for running a real-world patient-provider matching system inspired by our results.

Problem

• Optimize patient-provider matching
• Reduce rematching workload
• Improve match quality

Innovation

• Assortment optimization for matching
• Simultaneous provider menu offering
• Tailored assortment sizes improvement