Federated AI improves pancreatic cancer treatment while protecting patient data
A Federated Artificial Intelligence Framework for Optimizing Pancreatic Cancer Treatment - Strategy Update
Machine Learning
Summary
Pancreatic cancer treatment can improve if doctors use data from many hospitals, but sharing patient data centrally is tough due to privacy rules. The authors describe their work on a federated artificial intelligence system that allows hospitals to collaboratively analyze data without sharing it centrally. They set up a technical system at different hospitals to train AI models locally, combining results safely to identify cancer subtypes and optimize treatments. Their approach manages differences in local data well and overcomes administrative and ethical challenges, although expanding to many more hospitals remains difficult.
What this means in practice
- •For hospital data teams: Set up AI pipelines that train models on local patient data to improve pancreatic cancer subtype diagnosis without sharing raw data outside the hospital.
- •For clinical ai developers: Develop federated algorithms that handle different feature sets from multiple hospitals to collaboratively analyze cancer data under privacy regulations.
Authors
Anne-Christin Hauschild, Amirreza Aleyasin, Nils H. Beyer, Lisa Fricke, Jonas Hügel, Maryam Moradpour, Anh-Tien Nguyen, Youngjun Park, Sophia Rheinländer, Tim Beissbarth, Elisabeth Hessmann, Martin Middeke, Matthias Lauth, Maximilian Reichert, Ulrich Sax
Abstract
While a centralized approach involving patient consent to collect and analyze data centrally would theoretically offer the best data quality and predictive performance, it is not always feasible in practice. Federated Learning (FL) architectures have shown to be a very promising approach to use and access distributed disease related resources within the GDPR boundaries. In a previous case report, we described the preconditions at the participating sites and necessary administrative and process related steps to prepare data, people and infrastructure for improving subtype identification and assessing treatment options in pancreatic cancer. We update this report sharing our experience in tackling the challenges and show preliminary results of the actual federated learning AI pipelines. At the participating sites, we have to identify and annotate the data being accessible after extraction and transformation in a local FL hub - in our case a centrally developed and distributively deployed Docker container. This container comprises the FL scripts generating local models. We apply a newly developed FL algorithm considering all local features, including partial overlapping features specific to the local sites. Theoretically, an annotation in a cancer setting should succeed using the German oncology core data set (oBDS), which is already utilized for mandatory reporting to cancer registries, and can be sustained in the FL setting. The FL algorithms deal robustly with partially overlapping features as we showed with public data sets. Major roadblocks including straightening operational concepts for the infrastructures, ethics approval for such novel architectures and support for every site have been addressed. However, scaling up this approach in the future faces hurdles; while including broader multi-modal data sets should be feasible, large-scale deployment to more sites remains challenging.