Bringing the Algorithms to the Data -- Secure Distributed Medical Analytics using the Personal Health Train (PHT-meDIC)

TL;DR

The paper presents PHT-meDIC, an open-source system implementing the Personal Health Train paradigm to enable secure, privacy-preserving distributed medical data analysis across multiple sites using containerization.

Contribution

It introduces PHT-meDIC, a scalable, secure platform for distributed medical analytics that adheres to data privacy regulations and facilitates complex analysis pipelines.

Findings

Successful deployment on large-scale distributed data

Application of deep neural networks to medical images

Enhanced security and governance in distributed analysis

Abstract

The need for data privacy and security -- enforced through increasingly strict data protection regulations -- renders the use of healthcare data for machine learning difficult. In particular, the transfer of data between different hospitals is often not permissible and thus cross-site pooling of data not an option. The Personal Health Train (PHT) paradigm proposed within the GO-FAIR initiative implements an 'algorithm to the data' paradigm that ensures that distributed data can be accessed for analysis without transferring any sensitive data. We present PHT-meDIC, a productively deployed open-source implementation of the PHT concept. Containerization allows us to easily deploy even complex data analysis pipelines (e.g, genomics, image analysis) across multiple sites in a secure and scalable manner. We discuss the underlying technological concepts, security models, and governance processes. The implementation has been successfully applied to distributed analyses of large-scale data, including applications of deep neural networks to medical image data.