Privacy-preserving Artificial Intelligence Techniques in Biomedicine

Abstract

Artificial intelligence (AI) has been successfully applied in numerous scientific domains. In biomedicine, AI has already shown tremendous potential, e.g. in the interpretation of next-generation sequencing data and in the design of clinical decision support systems. However, training an AI model on sensitive data raises concerns about the privacy of individual participants. For example, summary statistics of a genome-wide association study can be used to determine the presence or absence of an individual in a given dataset. This considerable privacy risk has led to restrictions in accessing genomic and other biomedical data, which is detrimental for collaborative research and impedes scientific progress. Hence, there has been a substantial effort to develop AI methods that can learn from sensitive data while protecting individuals' privacy. This paper provides a structured overview of recent advances in privacy-preserving AI techniques in biomedicine. It places the most important state-of-the-art approaches within a unified taxonomy and discusses their strengths, limitations, and open problems. As the most promising direction, we suggest combining federated machine learning as a more scalable approach with other additional privacy preserving techniques. This would allow to merge the advantages to provide privacy guarantees in a distributed way for biomedical applications. Nonetheless, more research is necessary as hybrid approaches pose new challenges such as additional network or computation overhead.

arXiv comment17 pages, 3 figures, 3 tables. Methods of Information in Medicine (2022)

References in corpus (35)

• A Survey on Deep Learning in Medical Image Analysis
• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Automatic chemical design using a data-driven continuous representation of molecules
• The Future of Digital Health with Federated Learning
• Convolutional Sequence to Sequence Learning
• Federated Learning with Non-IID Data
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Secure Federated Transfer Learning
• A Survey on Multi-Task Learning
• Differentially Private Federated Learning: A Client Level Perspective
• The Microsoft 2017 Conversational Speech Recognition System
• Assessment of algorithms for mitosis detection in breast cancer histopathology images
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• A generic framework for privacy preserving deep learning
• A simple and practical algorithm for differentially private data release
• LoPub: High-Dimensional Crowdsourced Data Publication with Local Differential Privacy
• Differential Privacy-enabled Federated Learning for Sensitive Health Data
• Split learning for health: Distributed deep learning without sharing raw patient data
• Variational Federated Multi-Task Learning
• Federated Multi-Task Learning
• Towards Formalizing the GDPR's Notion of Singling Out
• Communication-Efficient Distributed Deep Learning: A Comprehensive Survey
• Federated Learning with Differential Privacy: Algorithms and Performance Analysis
• Split Learning for collaborative deep learning in healthcare
• Federated Learning for Healthcare Informatics
• FADL:Federated-Autonomous Deep Learning for Distributed Electronic Health Record
• Privacy-preserving Federated Brain Tumour Segmentation
• FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare
• Privacy-Preserving Distributed Deep Learning for Clinical Data
• Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results
• Efficient differentially private learning improves drug sensitivity prediction
• Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation
• Conditionals in Homomorphic Encryption and Machine Learning Applications
• Secure multi-party linear regression at plaintext speed

Cited by in corpus (2)

• HyFed: A Hybrid Federated Framework for Privacy-preserving Machine Learning
• Flimma: a federated and privacy-preserving tool for differential gene expression analysis