[IISE Faculty List] Healthcare Big Data Analytics and Management| Conference Notice

[Mingyang Li]

Conference Notice


The 25th Online Public Forum for Engineering Management will focus on "Healthcare Big Data Analytics and Management" and will take place on March 15, 2023, from 9:00-11:00 am (CST) via Zoom (ID: 867 3245 3358, Code: 544896). The forum is organized by the Frontiers of Engineering Management and the School of Management at Huazhong University of Science and Technology.


     Dr. Qingpeng Zhang, Associate Professor in the School of Data Science at City University of Hong Kong, will host the forum, and we have invited four experts in the field to share their research on this important topic: Dr. Mingyang Li, Associate Professor in the Department of Industrial and Management Systems Engineering at the University of South Florida; Dr. Jiaheng Xie, Assistant Professor in the Lerner College of Business & Economics at the University of Delaware; Dr. Yong-Hong Kuo, Assistant Professor in the Department of Industrial and Manufacturing Systems Engineering at the University of Hong Kong; and Dr. Xiaoying Tang, Assistant Professor the Department of Electronic and Electrical Engineering at Southern University of Science and Technology.


      We welcome all teachers and students who are interested in this subject to join us for what promises to be an informative and engaging event.





Frontiers of Engineering Management

School of Management, Huazhong University of Science and Technology

March 9th, 2023


Agenda

Conference Time：9:00-11:00am, 15th March（the standard Beijing time）

Zoom ID：867 3245 3358 (Code: 544896)

Moderator：Qingpeng Zhang, Associate Professor, City University of Hong Kong


· 9:00-9:30

Heterogeneous Healthcare Outcome Modeling of Older Adult Populations: A Latent Variable Approach

【Mingyang Li  University of  South Florida】

· 9:30-10:00

Care for the Mind Amid Chronic Diseases: An Interpretable AI Approach Using IoT

【Jiaheng Xie  University of Delaware】

· 10:00-10:30

Operations Research and Data Science for Hospital Emergency Department Operations

【Yong-Hong Kuo  University of Hong Kong】

· 10:30-11:00

Zero/One-shot Fundus Anomaly Detection

【Xiaoying Tang  Southern University of Science and Technology】




Introduction of Keynote Speakers

[Image]


Mingyang Li an Associate Professor in the Department of Industrial and Management Systems Engineering at the University of South Florida. He received his PhD in Systems and Industrial Engineering from the University of Arizona. His research interests focus on data analytics and system informatics with diverse applications in areas such as reliability & quality, healthcare, energy, homeland security, and manufacturing. His research has been published in journals such as IISE Transactions, IISE Transactions on Healthcare Systems Engineering, Health Care Management Science, and IEEE Transactions on Reliability and Journal of Quality Technology.


【Abstract】

Studying healthcare outcomes in older adults often entails analysis of data presented as either time-to-event observations (e.g., time-to-hospitalization), or longitudinal trajectories (e.g., disability progression). The heterogeneity present in such data presents opportunities to both understand individual-level healthcare utilization patterns and propose optimal, proactive resource planning strategies. In this talk, we will introduce a series of latent variable modeling approaches that considers both observed and unobserved factors for modeling (1) hospital time-to-readmission risk, and (2) clinical progression of community-dwelling older adults. Real world case studies will be provided to illustrate the performance advantages of the aforementioned modeling approaches as well as the practical benefits to stakeholders.


[Image]


Jiaheng Xie an Assistant Professor in the Lerner College of Business & Economics, University of Delaware. He received his PhD in Management Information Systemsfrom the University of Arizona. His research interests focus on deep learning, NLP and multimodal machine learning with diverse applications in areas such as health risk analysis, misinformation and IOT sensors. His research has been published in leading IS journals such as MIS Quarterly and JMIS.


【Abstract】

Health sensing for chronic disease management creates immense benefits for social welfare. Existing health sensing studies primarily focus on the prediction of physical chronic diseases. Depression, a widespread complication of chronic diseases, is however understudied. We draw on the medical literature to support depression prediction using motion sensor data. To connect human expertise in the decision-making, safeguard trust for this high-stake prediction, and ensure algorithm transparency, we develop an interpretable deep learning model: Temporal Prototype Network (TempPNet). TempPNet is built upon the emergent prototype learning models. To accommodate the temporal characteristic of sensor data and the progressive property of depression, TempPNet differs from existing prototype learning models in its capability of capturing the temporal progression of depression. Extensive empirical analyses using real-world motion sensor data show that TempPNet outperforms state-of-the-art benchmarks in depression prediction. Moreover, TempPNet interprets its predictions by visualizing the temporal progression of depression and its corresponding symptoms detected from sensor data. We further conduct a user study to demonstrate its superiority over the benchmarks in interpretability. This study offers an algorithmic solution for impactful social good — collaborative care of chronic diseases and depression in health sensing. Methodologically, it contributes to extant literature with a novel interpretable deep learning model for depression prediction from sensor data. Patients, doctors, and caregivers can deploy our model on mobile devices to monitor patients’ depression risks in real-time. Our model’s interpretability also allows human experts to participate in the decision-making by reviewing the interpretation of prediction outcomes and making informed interventions.


[Image]


Yong-Hong Kuo is Assistant Professor in the Department of Industrial and Manufacturing Systems Engineering, the University of Hong Kong. He earned his B.Sc. in Mathematics, with a minor in Risk Management Science, and M.Phil. and Ph.D. in Systems Engineering and Engineering Management, from the Chinese University of Hong Kong. During the period, he also worked at the University of California at Berkeley as Visiting Researcher and Oak Ridge National Laboratory as Visiting Student. Prior to joining HKU, he was Research Assistant Professor at Stanley Ho Big Data Decision Analytics Research Centre, the Chinese University of Hong Kong.


【Abstract】

In this talk, we will present our applications of operations research and data science techniques for managing operations in a hospital emergency department (ED) in Hong Kong. There are three main applications to be presented.

The objective of the first application is to apply machine learning algorithms for real-time and personalized patient waiting time prediction. We also aim to introduce the concept of systems thinking to enhance the performance of the prediction models. We found that Machine learning algorithms with the utilization of the systems knowledge could significantly improve the performance of waiting time prediction. Waiting time prediction for less urgent patients is more challenging.

In the second application, we use simulation to analyze patient flows in the ED. When developing the simulation model, we faced the challenge that the data kept by the ED were incomplete so that the service-time distributions were not directly obtainable. We propose a simulation-optimization approach (integrating simulation with meta-heuristics) to obtain a good set of estimate of input parameters of our simulation model. Using the simulation model, we evaluate the impact of possible changes to the system by running different scenarios.

In the third application, we investigate an ED staff scheduling problem with two types of patient groups: patients with serious (life-threatening) health conditions and those with stable health symptoms. We employ a chance constraint-based minimum staffing level parameter in our staffing and scheduling optimization model that guarantees the service start for priority patients within a given amount of time during each time interval. A heuristic framework is also proposed that utilizes the transient analysis results to solve the optimization model in order to find the right staffing levels against each time period. The results of the heuristic framework demonstrate the effectiveness of our approach as staffing levels are determined by respecting the service start time guaranties and rush hours in the ED.


[Image]


Xiaoying Tang is an Assistant Professor and Associate Researcher at the Department of Electronic and Electrical Engineering at Southern University of Science and Technology, Adjunct Assistant Professor at the Department of Electrical and Computer Engineering at Johns Hopkins University, Adjunct Assistant Professor at the Department of Electrical and Computer Engineering at Carnegie Mellon University, PI for the National Natural Science Foundation of China and the National Key R&D Program of China, Associate Editor for Neural Networks and Frontiers in Neuroscience, Area Chair/Session Chair of MICCAI/IEEE ISBI/IEEE EMBC/ICPR conferences, IEEE senior member. Dr. Tang specializes in medical image analysis, pattern recognition, and medical artificial intelligence.


【Abstract】

Zero/one-shot anomaly detection is a challenging problem in fundus image analysis, aiming to detect rare and subtle anomalies in fundus images with limited labeled data. In this context, zero-shot learning refers to detecting anomalies of unseen classes without any labeled abnormal examples, while one-shot learning refers to detecting anomalies of unseen classes with only one labeled abnormal example. However, the performance of existing anomaly detection methods remains unsatisfactory due to the complex and heterogeneous nature of fundus images. To address this issue, this talk discusses our solutions for zero/one-shot fundus anomaly detection: (1) We propose an unsupervised anomaly detection framework for diabetic retinopathy (DR) identification from fundus images, named Lesion2Void. (2) We present a novel one-shot anomaly detection framework (named AugPaste) for DR anomaly detection in fundus images.


Introduction of Moderator

[Image]


Qingpeng Zhang is an Associate Professor with the School of Data Science, City University of Hong Kong. He received the BSc degree in Automation from Huazhong University of Science and Technology, and the PhD degree in Systems and Industrial Engineering from the University of Arizona. His research interests focus on medical informatics, AI in medicine and complex networks. His research appeared in journals such as Nature Human Behaviour and Nature Communications. He received the President’s Award (2022) and the Outstanding Research Award (2021) from CityU.



Background

Frontiers of Engineering Management

Frontiers of Engineering Management (FEM) is a quarterly research journal that is supervised by the Chinese Academy of Engineering and administered jointly by Higher Education Press, Tsinghua University, and Huazhong University of Science and Technology. It is published in English, both in print and online, and is designed to provide an international platform for academicians, researchers, professionals, and practitioners in the broad field of engineering management to share knowledge in the form of research articles, reviews, comments, and super engineering.

FEM is organized in an international dimension and strives to promote the advancement of the science of engineering management, improve the practice of engineering management, and prepare practitioners and researchers in the field. With its high-quality contributions, FEM plays an important role in fostering collaborations and advancing the state of the art in engineering management.


Online Public Forum for Engineering Management

Since the end of 2020, the Frontiers of Engineering Management editorial office has launched a series of successful Online Public Forums for Engineering Management, which have attracted many researchers from across China. These forums feature keynote speeches from academicians, renowned experts, and authors of FEM, both from China and abroad.

As a platform for sharing knowledge and fostering collaboration, the Online Public Forum for Engineering Management has been an important part of FEM's efforts to promote the advancement of the science and practice of engineering management. Through these events, FEM has helped to connect researchers, practitioners, and experts in the field, and to provide valuable insights into the latest research and trends in engineering management.



[Image]Scan the code and follow us
[Image]Frontiers of Engineering Management

Yong LIHuiwen DONG Tel：+86-27-87540191
E-mail：fem at hust.edu.cn
  Linan ZHANG
 Tel：+86-10-58581429
E-mail：zhangln at hep.com.cn
Website：
https://mc.manuscriptcentral.com/femhttp://journal.hep.com.cn/femhttps://www.springer.com/journal/42524https://www.engineering.org.cn/ch/journal/fem




Mingyang Li, Ph.D.

Associate Professor

Department of Industrial and Management Systems Engineering

University of South Florida

Tampa, Florida 33620

Phone: (813) 974-5579

Email: mingyangli at usf.edu

URL: http://imse.eng.usf.edu

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.clemson.edu/pipermail/iefac.list/attachments/20230310/b3b1147c/attachment-0001.htm>