Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data

Abstract

Several studies underscore the potential of deep learning in identifying complex patterns, leading to diagnostic and prognostic biomarkers. Identifying sufficiently large and diverse datasets, required for training, is a significant challenge in medicine and can rarely be found in individual institutions. Multi-institutional collaborations based on centrally-shared patient data face privacy and ownership challenges. federated learning is a novel paradigm for data-private multi-institutional collaborations, where model-learning leverages all available data without sharing data between institutions, by distributing the model-training to the data-owners and aggregating their results. We show that federated learning among 10 institutions results in models reaching 99% of the model quality achieved with centralized data, and evaluate generalizability on data from institutions outside the federation. We further investigate the effects of data distribution across collaborating institutions on model quality and learning patterns, indicating that increased access to data through data private multi-institutional collaborations can benefit model quality more than the errors introduced by the collaborative method. finally, we compare with other collaborative-learning approaches demonstrating the superiority of federated learning, and discuss practical implementation considerations. clinical adoption of federated learning is expected to lead to models trained on datasets of unprecedented size, hence have a catalytic impact towards precision/personalized medicine. Abbreviations CDS Collaborative data sharing FL Federated learning IIL Institutional incremental learning CIIL Cyclic institutional incremental learning IID Independent and identically distributed BraTS Brain tumor segmentation

Comparison and interpretability of machine learning models to predict severity of chest injury

“…Furthermore, the use of CUIs as coded structured data from the free text allows for portability of classifiers by sharing the CUI vocabulary of trained models, enabling centers to aggregate data without leakage of PHI. 38 The multiple facets described have broad implications for building accurate and interpretable ML models to populate complex data fields within clinical registries to identify practice gaps and inform improvements in patient care.…”

Truly Privacy-Preserving Federated Analytics for Precision Medicine with Multiparty Homomorphic Encryption

“…Similar to existing federated-learning solutions, FAMHE enables a large number of data providers to keep their data locally stored under their control and to effectively collaborate in order to perform large-scale analyses. However, contrary to most federated-learning solutions 2,3,3,6,15,16 , FAMHE also protects data confidentiality and does not require the addition of any noise to the results. As other proposed solutions based on advanced cryptography [17][18][19][20][21]37 , FAMHE does not reveal intermediate values to any party.…”

Federated Learning used for predicting outcomes in SARS-COV-2 patients

“…The authors chose FL due to its ability to rapidly launch centrally orchestrated experiments with improved traceability of data and assessment of algorithmic changes and impact 29 . FL has shown promise in recent medical imaging applications [30][31][32][33] , including COVID-19 analysis [34][35][36][37] , albeit with limited scale. Governance of data for FL is maintained locally, alleviating privacy concerns, with only model 'weights' or 'gradients' transferred between the client-sites and the federated server 38,39 .…”