Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data
Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data
复制标题
DOI：
10.1038/s41598-020-69250-1
复制
发表时间：
2020-07-28
影响因子：
4.6
通讯作者：
Bakas, Spyridon
中科院分区：
文献类型：
--
作者：
Sheller, Micah J.;Edwards, Brandon;Bakas, Spyridon
多项研究强调了深度学习在识别复杂模式方面的潜力，从而产生诊断和预后生物标志物。识别培训所需的足够大且多样化的数据集是医学领域的一项重大挑战，并且在单个机构中很少能找到。基于集中共享患者数据的多机构协作面临隐私和所有权挑战。联邦学习是数据私有多机构协作的一种新颖范式，其中模型学习通过将模型训练分发给数据所有者并汇总其结果来利用所有可用数据，而无需在机构之间共享数据。我们表明，10 个机构之间的联邦学习使模型达到了集中数据模型质量的 99%，并评估了联邦以外机构数据的通用性。我们进一步研究了合作机构之间的数据分布对模型质量和学习模式的影响，表明通过数据私有多机构合作增加对数据的访问比协作方法引入的错误更有利于模型质量。最后，我们与其他协作学习方法进行比较，证明联邦学习的优越性，并讨论实际的实施注意事项。联合学习的临床采用预计将导致在前所未有的规模数据集上训练模型，从而对精准/个性化医疗产生催化影响。
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.