Feasibility study of multi-site split learning for privacy-preserving medical systems under data imbalance constraints in COVID-19, X-ray, and cholesterol dataset

Yoo Jeong Ha,Minjae Yoo,Soyi Jung,Seehwan Yoo,Joongheon Kim,Gusang Lee

doi:10.1038/s41598-022-05615-y

Yoo Jeong Ha, Minjae Yoo + Show 4 more

Open Access

https://doi.org/10.1038/s41598-022-05615-y

Copy DOI

Abstract

It seems as though progressively more people are in the race to upload content, data, and information online; and hospitals haven’t neglected this trend either. Hospitals are now at the forefront for multi-site medical data sharing to provide ground-breaking advancements in the way health records are shared and patients are diagnosed. Sharing of medical data is essential in modern medical research. Yet, as with all data sharing technology, the challenge is to balance improved treatment with protecting patient’s personal information. This paper provides a novel split learning algorithm coined the term, “multi-site split learning”, which enables a secure transfer of medical data between multiple hospitals without fear of exposing personal data contained in patient records. It also explores the effects of varying the number of end-systems and the ratio of data-imbalance on the deep learning performance. A guideline for the most optimal configuration of split learning that ensures privacy of patient data whilst achieving performance is empirically given. We argue the benefits of our multi-site split learning algorithm, especially regarding the privacy preserving factor, using CT scans of COVID-19 patients, X-ray bone scans, and cholesterol level medical data.

Highlights

The world was met with a demise when the lethal Coronavirus Disease 2019 (COVID-19) began taking away the lives of loved ones
The ominous presence of hackers in cyberspace creates a fear of leaks of sensitive patient information wherever it gets transferred
To provide a solution to the practice of maintaining the confidentiality of patient information, we introduced multi-site split learning

Summary

Introduction

The world was met with a demise when the lethal Coronavirus Disease 2019 (COVID-19) began taking away the lives of loved ones. This paper aims to furnish a secure learning process where hospitals all over the globe can share their findings to create a deep learning model without revealing any sensitive patient information This new technique allows hospitals to share their data without sending raw medical images to external associations. The main research goal of this paper is to test the effect of varying the number of participating hospitals, which are called end-systems, and the data ratio on the performance of our multi-site split learning algorithm. Through this paper’s experimental findings on the optimal client number and data split ratio, we hope researchers would use our guidance to hastily practice split learning while protecting the personal information of patient records

Objectives

Methods

Results

Discussion

Conclusion