I-ETL: an interoperability-aware health (meta) data pipeline to enable federated analyses

Abstract

Clinicians are interested in better understanding complex diseases, such as cancer or rare diseases, so they need to produce and exchange data to mutualize sources and join forces. To do so and ensure privacy, a natural way consists in using a decentralized architecture and Federated Learning algorithms. This ensures that data stays in the organization in which it has been collected, but requires data to be collected in similar settings and similar models. In practice, this is often not the case because healthcare institutions work individually with different representations and raw data; they do not have means to normalize their data, and even less to do so across centers. For instance, clinicians have at hand phenotypic, clinical, imaging and genomic data (each individually collected) and want to better understand some diseases by analyzing them together. This example highlights the needs and challenges for a cooperative use of this wealth of information. We designed and implemented a framework, named I-ETL, for integrating highly heterogeneous healthcare datasets of hospitals in interoperable databases. Our proposal is twofold: (i) we devise two general and extensible conceptual models for modeling both data and metadata and (ii) we propose an Extract-Transform-Load (ETL) pipeline ensuring and assessing interoperability from the start. By conducting experiments on open-source datasets, we show that I-ETL succeeds in representing various health datasets in a unified way thanks to our two general conceptual models. Next, we demonstrate the importance of blending interoperability as a first-class citizen in integration pipelines, ensuring possible collaboration between different centers.