Journal of Healthcare Informatics Research · 2023 · 15 citations · 35 references
ComputingComputer ScienceHealth InformaticsHealth Information PrivacyMachine LearningPrivacy EngineeringEnsemble LearningEnsemble MethodsFederated LearningFederated Learning PrivacyMachine Learning For Big DataPatient Privacy12-Lead ElectrocardiographyEcg Beat ClassificationMetricsPrivacyPrivacy-preserving LearningPrivacy-preserving Machine LearningReal-world ApplicationWeighted Voting
Artificial intelligence and machine learning have led to prominent and spectacular innovations in various scenarios. Application in medicine, however, can be challenging due to privacy concerns and strict legal regulations. Methods that centralize knowledge instead of data could address this issue. In this work, 6 different decentralized machine learning algorithms are applied to 12-lead ECG classification and compared to conventional, centralized machine learning. The results show that state-of-the-art federated learning leads to reasonable losses of classification performance compared to a standard, central model (-0.054 AUROC) while providing a significantly higher level of privacy. A proposed weighted variant of federated learning (-0.049 AUROC) and an ensemble (-0.035 AUROC) outperformed the standard federated learning algorithm. Overall, considering multiple metrics, the novel batch-wise sequential learning scheme performed best (-0.036 AUROC to baseline). Although, the technical aspects of implementing them in a real-world application are to be carefully considered, the described algorithms constitute a way forward towards preserving-preserving AI in medicine.
35
PhysioBank, PhysioToolkit, and PhysioNet
Ary L. Goldberger, Luı́s A. Nunes Amaral, Leon Glass et al. · Circulation · 2000 · 14.5K citations · Full text
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
1993 · 14.3K citations
Ashwin Machanavajjhala, Daniel Kifer, Johannes Gehrke et al. · ACM Transactions on Knowledge Discovery from Data · 2007 · 3.6K citations