Affordable Access

Access to the full text

Decentralized Learning with Virtual Patients for Medical Diagnosis of Diabetes

Authors
  • Takahashi, Yuta1
  • Chang, Han-ten1
  • Nakai, Akie1
  • Kagawa, Rina1
  • Ando, Hiroyasu1, 2
  • Imakura, Akira1, 1
  • Okada, Yukihiko1, 1
  • Tsurushima, Hideo1
  • Suzuki, Kenji1, 1
  • Sakurai, Tetsuya1, 1
  • 1 University of Tsukuba, Tsukuba, Japan , Tsukuba (Japan)
  • 2 Tohoku University, Sendai, Japan , Sendai (Japan)
Type
Published Article
Journal
SN Computer Science
Publisher
Springer Singapore
Publication Date
Apr 25, 2021
Volume
2
Issue
4
Identifiers
DOI: 10.1007/s42979-021-00564-1
Source
Springer Nature
Keywords
License
Green

Abstract

Machine learning, applied to medical data, can uncover new knowledge and support medical practices. However, analyzing medical data by machine learning methods presents a trade-off between accuracy and privacy. To overcome the trade-off, we apply the data collaboration analysis method to medical data. This method using artificial dummy data enables analysis to compare distributed information without using the original data. The purpose of our experiment is to identify patients diagnosed with diabetes mellitus (DM), using 29,802 instances of real data obtained from the University of Tsukuba Hospital between 01/03/2013 and 30/09/2018. The whole data is divided into a number of datasets to simulate different hospitals. We propose the following improvements for the data collaboration analysis. (1) Making the dummy data which has a reality and (2) using non-linear reconverting functions into the comparable space. Both can be realized using the generative adversarial network (GAN) and Node2Vec, respectively. The improvement effects of dummy data with GAN scores more than 10% over the effects of dummy data with random numbers. Furthermore, the improvement effect of the re-conversion by Node2Vec with GAN anchor data scores about 20% higher than the linear method with random dummy data. Our results reveal that the data collaboration method with appropriate modifications, depending on data type, improves analysis performance.

Report this publication

Statistics

Seen <100 times