Matching Patients with Surgeons: Heterogeneous Effects of Surgical Volume on Surgery Duration
Behrooz Pourghannad, Guihua Wang
Manufacturing & Service Operations Management · 2025 · Volume 27 · Issue 4
Abstract
Problem definition : We study how to leverage patient-specific information to improve a hospital’s operational efficiency. We use abdominal surgery as the clinical setting and study the heterogeneous effects of surgical volume on surgery duration. We develop a framework for using patient-specific information by addressing three important questions: (1) Is the effect of surgical volume heterogeneous across patients with different features? (2) If so, how could patient-specific information that captures the heterogeneous effects of surgical volume on surgery duration be generated? (3) What is the value of patient-specific information in helping a hospital improve its operational efficiency? Methodology/results : Using an instrumental variable approach to address potential endogeneity issues, we first use a regression model to show that the average effect of surgical volume on surgery duration is significant. Then, we use a regression model with interaction terms to show that the effect of surgical volume is heterogeneous. After that, we apply an instrumental variable forest approach to obtain patient-specific volume effects. Finally, we use patient-specific volume effects and an optimization model to assess the potential value of patient-specific information in improving a hospital’s operational efficiency. We find the that total duration of surgeries could be reduced by 2.5%–8.9% if patient-specific volume effects are considered. Managerial implications : This study provides a framework for understanding treatment effect heterogeneity and using patient-specific information to improve a hospital’s operational efficiency. We provide empirical evidence that the effect of surgical volume is heterogeneous and address the challenges of estimating heterogeneous effects for different patients. Our framework can help hospital administrators to better match patients with surgeons, improving a hospital’s operational efficiency. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2023.0019 .
Keywords
causal inference, machine learning, surgeon experience, surgery scheduling
Enable JavaScript for citation tools and additional paper interactions.