ZTE Communications ›› 2022, Vol. 20 ›› Issue (3): 3-16.doi: 10.12142/ZTECOM.202203002

• Special Topic • Previous Articles     Next Articles

A Collaborative Medical Diagnosis System Without Sharing Patient Data

NAN Yucen1(), FANG Minghao2, ZOU Xiaojing2, DOU Yutao3, ZOMAYA Albert Y.3   

  1. 1.College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410003, China
    2.Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430074, China
    3.Center for Distributed and High Performance Computing, University of Sydney, Sydney 2008, Australia
  • Received:2022-06-10 Online:2022-09-13 Published:2022-09-14
  • About author:NAN Yucen (yucen.nan@sydney.edu.au) received her PhD and MPhil degrees from University of Sydney, Australia in 2022 and 2017. She is currently a lecturer in the College of Intelligence Science and Technology, National University of Defense Technology, China. Her current research interests are in the area of edge computing and the Internet of Things.|FANG Minghao received his MD degree from Huazhong University of Science and Technology, China in 2006. He is currently an associate professor with Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology. He has worked in emergency and critical care medicine for 20 years. His research interests include the diagnosis and treatment of critical respiratory and cardiovascular disease.|ZOU Xiaojing received her MD degree from Tongji Medical College, Huazhong University of Science and Technology, China in 2011. She is an associate chief physician in Emergency Department and Intensive Care Unit of Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology. Her research interests are in sepsis and the application of artificial intelligence in critical diseases.|DOU Yutao received his BE degree in software engineering from University of Canberra, Australia in 2020. He is currently working toward the master of philosophy degree with the University of Sydney, Australia. His research interests mainly include distributed computing, bioinformatics, and artificial intelligence.|Albert Y. ZOMAYA is the chair professor of high performance computing & networking in the School of Computer Science and Director of the Center for Distributed and High Performance Computing at the University of Sydney, Australia. He has published more than 600 scientific papers and is the (co-)author/editor of more than 30 books. As a sought-after speaker, he has delivered more than 190 keynote addresses, invited seminars, and media briefings. His research interests span several areas in parallel and distributed computing and complex systems. He is currently the Editor in Chief of the ACM Computing Surveys and served in the past as Editor in Chief of the IEEE Transactions on Computers (2010—2014) and the IEEE Transactions on Sustainable Computing (2016—2020).

Abstract:

As more medical data become digitalized, machine learning is regarded as a promising tool for constructing medical decision support systems. Even with vast medical data volumes, machine learning is still not fully exploiting its potential because the data usually sits in data silos, and privacy and security regulations restrict their access and use. To address these issues, we built a secured and explainable machine learning framework, called explainable federated XGBoost (EXPERTS), which can share valuable information among different medical institutions to improve the learning results without sharing the patients’ data. It also reveals how the machine makes a decision through eigenvalues to offer a more insightful answer to medical professionals. To study the performance, we evaluate our approach by real-world datasets, and our approach outperforms the benchmark algorithms under both federated learning and non-federated learning frameworks.

Key words: explainable machine learning, federated learning, secured data analysis, medical applications