The future of digital health with federated learning

  title={The future of digital health with federated learning},
  author={Nicola Rieke and Jonny Hancox and Wenqi Li and Fausto Milletari and Holger R. Roth and Shadi Albarqouni and Spyridon Bakas and Mathieu Galtier and Bennett A. Landman and Klaus H. Maier-Hein and S{\'e}bastien Ourselin and Micah J. Sheller and Ronald M. Summers and Andrew Trask and Daguang Xu and Maximilian Baust and Manuel Jorge Cardoso},
  journal={NPJ Digital Medicine},
Data-driven machine learning (ML) has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems. Existing medical data is not fully exploited by ML primarily because it sits in data silos and privacy concerns restrict access to this data. However, without access to sufficient data, ML will be prevented from reaching its full potential and, ultimately, from making the transition from… 

Inverse Distance Aggregation for Federated Learning with Non-IID Data

IDA (Inverse Distance Aggregation), a novel adaptive weighting approach for clients based on meta-information which handles unbalanced and non-iid data which is highly plausible in medical data.

Surgical Data Science - from Concepts to Clinical Translation

An extensive review of current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to surgical data science, namely technical infrastructure for data acquisition, storage and access in the presence of regulatory constraints.

Federated Learning for Breast Density Classification: A Real-World Implementation

This study investigates the use of federated learning (FL) to build medical imaging classification models in a real-world collaborative setting and shows that despite substantial differences among the datasets from all sites and without centralizing data, it can successfully train AI models in federation.

Flimma: a federated and privacy-preserving tool for differential gene expression analysis.

Fimma addresses the issue of inhomogeneously distributed class labels or confounders in meta-analyses by implementing the state-of-the-art gene expression workflow limma voom in a federated, privacy-preserving manner.


  • Computer Science
  • 2022
A federated Cox model is presented that accommodates this data setting and also relaxes the proportional hazards assumption, allowing time-varying covariate effects, reducing upfront organisational costs compared to previous works.

A Federated Cox Model with Non-Proportional Hazards

A federated Cox model is presented that accommodates this data setting and also relaxes the proportional hazards assumption, allowing time-varying covariate effects, reducing upfront organisational costs compared to previous works.

A systematic review of federated learning applications for biomedical data

Federated learning is a growing field in machine learning with many promising uses in healthcare but investigators can do more to address the risk of bias and increase transparency by adding steps for data homogeneity or sharing required metadata and code.

Applying Machine Learning in Distributed Data Networks for Pharmacoepidemiologic and Pharmacovigilance Studies: Opportunities, Challenges, and Considerations

The time is ripe for the emerging interest to use data- Adaptive machine learning techniques in DDNs, and the utility of these data-adaptive modeling techniques in pharmacoepidemiologic and pharmacovigilance studies will likely continue to increase in the coming years.

A Systematic Literature Review on Federated Learning: From A Model Quality Perspective

This paper systematically reviews and objectively analyzes the approaches to improving the quality of Federated Learning models, and proposes an FL application framework for practitioners.



Federated Learning for Healthcare Informatics

  • Jie XuFei Wang
  • Medicine, Political Science
    J. Heal. Informatics Res.
  • 2021
The goal of this survey is to provide a review for federated learning technologies, particularly within the biomedical space, and summarize the general solutions to the statistical challenges, system challenges, and privacy issues in federation, and point out the implications and potentials in healthcare.

Federated Learning: Challenges, Methods, and Future Directions

The unique characteristics and challenges of federated learning are discussed, a broad overview of current approaches are provided, and several directions of future work that are relevant to a wide range of research communities are outlined.

Federated Learning with Non-IID Data

This work presents a strategy to improve training on non-IID data by creating a small subset of data which is globally shared between all the edge devices, and shows that accuracy can be increased by 30% for the CIFAR-10 dataset with only 5% globally shared data.

Privacy-preserving Federated Brain Tumour Segmentation

The feasibility of applying differential-privacy techniques to protect the patient data in a federated learning setup for brain tumour segmentation on the BraTS dataset is investigated and there is a trade-off between model performance and privacy protection costs.

Advances and Open Problems in Federated Learning

Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning

The overall effectiveness of FL for the challenging task of whole brain segmentation is demonstrated and it is observed that the proposed server-less BrainTorrent approach does not only outperform the traditional server-based one but reaches a similar performance to a model trained on pooled data.

Federated Machine Learning: Concept and Applications

This work proposes building data networks among organizations based on federated mechanisms as an effective solution to allow knowledge to be shared without compromising user privacy.

Federated Tensor Factorization for Computational Phenotyping

This paper developed secure data harmonization and federated computation procedures based on alternating direction method of multipliers (ADMM) and demonstrated with real medical datasets that the method resembles the centralized training model in terms of accuracy and phenotypes discovery while respecting privacy.