English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Electronic Health Records (EHR) data contains medical records such asdiagnoses, medications, procedures, and treatments of patients. This data isoften considered sensitive medical information. Therefore, the EHR data fromthe medical centers often cannot be shared, making it difficult to createprediction models using multi-center EHR data, which is essential for suchmodels' robustness and generalizability. Federated Learning (FL) is analgorithmic approach that allows learning a shared model using data in multiplelocations without the need to store all data in a central place. An example ofa prediction model's task is to predict future diseases. More specifically, themodel needs to predict patient's next visit diagnoses, based on current andprevious clinical data. Such a prediction model can support care providers inmaking clinical decisions and even provide preventive treatment. We propose afederated learning approach for learning medical concepts embedding. Thispre-trained model can be used for fine-tuning for specific downstream tasks.Our approach is based on an embedding model like BEHRT, a deep neural sequencetransduction model for EHR. We train using federated learning, both the MaskedLanguage Modeling (MLM) and the next visit downstream model. We demonstrate ourapproach on the MIMIC-IV dataset. We compare the performance of a model trainedwith FL against a model trained on centralized data. We find that our federatedlearning approach reaches very close to the performance of a centralized model,and it outperforms local models in terms of average precision. We also showthat pre-trained MLM improves the model's average precision performance in thenext visit prediction task, compared to an MLM model without pre-training. Ourcode is available at https://github.com/nadavlab/FederatedBEHRT.

Federated Learning of Medical Concepts Embedding using BEHRT