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

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.

An easy-to-use artificial intelligence preoperative lymph node metastasis predictor (LN-MASTER) in rectal cancer based on a privacy-preserving computing platform: multicenter retrospective cohort study

“…In addition, data security and privacy protection issues in the field of medicine leads to small sample sizes and lack of validation from external cohorts in clinical research. To address these issues, privacy-preserving methods have been invented and gradually used in healthcare multi-collaboration 17 , 27 . Federated learning is a collaborative learning technique among devices/organizations, wherein the model parameters from local models are shared and aggregated instead of sharing their local data 28 .…”

“…Therefore, innovative and effective solutions are necessary to address the conflicting interests of medical data protection and sharing. In this study, we applied a privacy-preserving computing platform (PPCP) to reconcile data confidentiality and privacy, while allowing data sharing or its application in model development from multiple sources without raw data exchange, to overcome the main barrier that limits data sharing 17 .…”

Quantum Distributed Deep Learning Architectures: Models, Discussions, and Applications

“…Analyzing and processing personal medical data is one of the most well-known distributed machine learning method applications. Research about analyzing medical data using classical Distributed Learning techniques such as [42]- [44] have already been thoroughly carried out, and research about using VQC to classify medical data, [45], in the quantum artificial intelligence field is ongoing as well. Considering the outstanding performance in data security and calculation efficiency of QDL, the medical industry must combine these researches and apply QDL in the medical field.…”

Entropy-Aware Similarity for Balanced Clustering: A Case Study With Melanoma Detection

“…1 [18]. Therefore, in recent years, computer-aided diagnosis (CAD) has been used in various medical fields [19], [20], [21], [22], and moreover, it has also been used to detect melanoma that requires early and accurate diagnosis [23].…”