Distinguished Lecturers

Dr. Jingshan Li received the BS, MS and PhD from Tsinghua University, Chinese Academy of Sciences, and University of Michigan, in 1989, 1992, and 2000, respectively. He was with GM R&D Center (2000­2006), and University of Kentucky (2006­2010). He is now a Professor in Department of Industrial and Systems Engineering, and Associate Director of Wisconsin Institute of Healthcare Systems Engineering, at University of Wisconsin-Madison. Dr. Li has published 1 textbook, 6 book volumes, 110 journal articles, 15 book chapters and 120 refereed conference proceedings. He is the Senior Editor of IEEE T­ASE and IEEE RA­L, and Department, Area, and Associate Editor of many other journals. He was General and Program Co­Chair of 2013 and 2015 IEEE CASE, and is the Program Chair in 2019. He was the founding Chair of Technical Committee on Sustainable Production Automation and has been the Chair of TC on Automation in Healthcare Management since 2016. Dr. Li is an IEEE Fellow. He received the NSF CAREER Award, IEEE RAS Early Career Award, and multiple Best Paper Awards from IEEE T­ASE, IIE Transactions, IEEE CASE, and many flagship international conferences. His research interests are in design, analysis, improvement and control of production and healthcare systems.

Talk # 1

From Industry 4.0 to Healthcare 4.0: Problems, Opportunities, and Challenges in Smart and Interconnected Healthcare Systems

In recent years, there have been growing interests in healthcare systems research worldwide to improve care quality, patient safety, and operation efficiency. In this talk, we will first discuss the evolution of Industry 4.0, then introduce the idea of Healthcare 4.0, i.e., the smart and interconnected healthcare systems. We will present lessons we learned and results we obtained during the journey of from manufacturing systems research to healthcare delivery system study. We will introduce the problems and issues, and then address the difficulties and opportunities in healthcare delivery systems. In addition, we will provide a brief description of recent studies in healthcare delivery systems carried out at the Production and Service Systems Lab in University of Wisconsin-Madison. Finally, we will discuss the challenges and future directions in smart and interconnected healthcare systems research.

Talk # 2

Smart and Efficient Healthcare Delivery throughout the Journey of Patient Care

A patient’s care journey may cover many aspects of healthcare delivery, from primary care, specialty care, emergency, hospitalization, to nursing facility and home care. Ensuring safe, efficient, and seamless care across the spectrum is of significant importance. In this talk, we will introduce the modeling and analysis for studying and improving the connected spectrums of healthcare system a patient may encounter throughout the care delivery cycle. Specifically, the workflow and coordination in primary care, the diagnosis and test procedures, the inpatient care and transitions between emergency, ICU and hospital floor, and the discharge, readmission, and home care interventions, will be addressed. Stochastic models, such as Markov chain, queueing networks, as well as machine learning and optimization techniques, and system-theoretic approach, will be utilized to analyze and improve the system performance. Multiple case studies on the hospital and clinic floors will be introduced. The successful development of such studies will contribute to developing smart and efficient healthcare delivery throughout the patient’s journey.

Prof. Jie Song is an Associate Professor with the Department of Industrial Engineering and Management, Peking University.She received the B.S. degree in applied mathematics from Peking University, Beijing, China, in 2004, and the M.S. and Ph.D. degree in industrial engineering from Tsinghua University, Beijing, in 2007 and 2010, respectively. She has been a research fellow in Georgia Institute of Technology and University of Wisconsin, Madison. Her current research interest is to develop novel methods/tools from an industrial engineering’s perspective by sufficiently understand the dynamic nature of the complex service engineering system in an information-rich environment, and appropriately integrating online learning knowledge to make real-time decision with purpose to improve the efficiency and effectiveness of service engineering systems. Her research is supported by National Science Foundation of China, she has been honored the Chang Jiang Youth Scholar Award by Ministry of Education in China and many other faculty awards in Peking University. She is also the winner of Best Paper Award of 2014 IEEE CASE. She is an Associate Editor for IEEE Automation of Science and Engineering, Flexible Services and Manufacturing, Asia-Pacific of Operational Research. Prof. Song is a professional member of IEEE and INFORMS.

Talk # 1

Dynamic recommendation of physician assortment with patient preference learning

Web-based appointment systems are emerging in healthcare industry providing patients with convenient and personalized services, among which physician recommendation is becoming more and more popular tool to make assignments of physicians to patients. Motivated by a popular physician recommendation application on a web-based appointment system in China, this paper gives a pioneer work in modelling and solving the physician recommendation problem. The application delivers personalized recommendations of physician assortments to patients with heterogeneous illness conditions, and then patients would select one physician for appointment according to their preferences. Capturing patient preferences is essential for physician recommendation delivery, however, it is also challenging due to the lack of data on patient preferences. In this work, we formulate the physician recommendation problem, based on which the preference learning algorithm is proposed that optimizes the recommendations and learns patient preferences at the same time. Since the illness conditions of patients are heterogeneous, the algorithm aims to make personalized recommendation for each patient. Besides demonstrating the effectiveness of algorithm performance in terms of regret bound, we also provide extensive numerical experiments to show the expected algorithm performance under heterogeneous reward scenarios and performance comparison with algorithms in literature under fixed reward scenarios. We introduce the flexibility of adjusting preference estimate update interval into our algorithm, and conclude that short update interval contributes to short-term performance while long update interval leads to good results in the long run. Furthermore, we analyse how preference bound helps the algorithm to make explorations, which constitute two major contributions of our algorithm. Finally, we discuss the relevance between patient preferences and physician utilization, and present a utilization-balancing approach that is effective in numerical experiments