Feature-Driven Robust Surgery Scheduling
Thu, Dec 01, 2022
Speaker:章宇 教授 西南财经大学
Date:Oct.13 2022 10:00
Tencent meeting:133 458 836
PW:461434
Abstract:
Patient features such as gender, age and underlying disease are crucial to improving model fidelity of surgery durations. In this paper, we study a robust surgery scheduling problem augmented by patient feature segmentation. We consider particularly the surgery-to-OR allocations for elective patients and future emergency patients. Using feature data, we classify patients into different types using machine learning methods and characterize the uncertain surgery duration via a feature-based cluster-wise ambiguity set. We propose a feature-driven adaptive robust optimization model that minimizes an overtime riskiness index, which helps to mitigate both the magnitude and probability of overtime. The model can be reformulated as a second-order cone optimization problem. From the reformulation, we elucidate that minimizing the overtime riskiness index is equivalent to minimizing a Fano factor. This renders our robust optimization model easily interpretable to healthcare practitioners. To efficiently solve the second-order cone optimization problem, we develop a branch-and-cut algorithm. Numerical experiments demonstrate that our model outperforms benchmark models in a variety of performance metric.
Bio:
章宇,西南财经大学教授、博导。东北大学本科、直博,新加坡国立大学联合培养博士、博后,并多次受邀访问。主要从事物流、供应链、交通、医疗服务运营管理中的鲁棒优化与决策研究。主持和参与国家自然科学基金项目3项。在Operations Research,Mathematical Programming,INFORMS Journal on Computing等期刊发表学术论文10余篇。获2019年管理科学与工程学会优秀博士学位论文奖,获2020年Omega期刊最佳论文奖,单篇论文入选ESI高被引论文。受邀担任Operations Research,Transportation Science,SIAM Journal on Optimization 等期刊匿名审稿人,担任中国运筹学会决策科学分会理事。
We protect your privacy. We use cookies to personalize content, provide features, and analyze traffic to our website anonymously and in a privacy compliant manner. By law, we may store cookies on your device if they are strictly necessary for the operation of this site. For all other cookie types, we need your permission. For more information, please see the privacy policy linked below.