@Article{info:doi/10.2196/47652,
author="Sp{\"a}th, Julian
and Sewald, Zeno
and Probul, Niklas
and Berland, Magali
and Almeida, Mathieu
and Pons, Nicolas
and Le Chatelier, Emmanuelle
and Gin{\`e}s, Pere
and Sol{\'e}, Cristina
and Juanola, Adri{\`a}
and Pauling, Josch
and Baumbach, Jan",
title="Privacy-Preserving Federated Survival Support Vector Machines for Cross-Institutional Time-To-Event Analysis: Algorithm Development and Validation",
journal="JMIR AI",
year="2024",
month="Mar",
day="29",
volume="3",
pages="e47652",
keywords="federated learning; survival analysis; support vector machine; machine learning; federated; algorithm; survival; FeatureCloud; predict; predictive; prediction; predictions; Implementation science; Implementation; centralized model; privacy regulation",
abstract="Background: Central collection of distributed medical patient data is problematic due to strict privacy regulations. Especially in clinical environments, such as clinical time-to-event studies, large sample sizes are critical but usually not available at a single institution. It has been shown recently that federated learning, combined with privacy-enhancing technologies, is an excellent and privacy-preserving alternative to data sharing. Objective: This study aims to develop and validate a privacy-preserving, federated survival support vector machine (SVM) and make it accessible for researchers to perform cross-institutional time-to-event analyses. Methods: We extended the survival SVM algorithm to be applicable in federated environments. We further implemented it as a FeatureCloud app, enabling it to run in the federated infrastructure provided by the FeatureCloud platform. Finally, we evaluated our algorithm on 3 benchmark data sets, a large sample size synthetic data set, and a real-world microbiome data set and compared the results to the corresponding central method. Results: Our federated survival SVM produces highly similar results to the centralized model on all data sets. The maximal difference between the model weights of the central model and the federated model was only 0.001, and the mean difference over all data sets was 0.0002. We further show that by including more data in the analysis through federated learning, predictions are more accurate even in the presence of site-dependent batch effects. Conclusions: The federated survival SVM extends the palette of federated time-to-event analysis methods by a robust machine learning approach. To our knowledge, the implemented FeatureCloud app is the first publicly available implementation of a federated survival SVM, is freely accessible for all kinds of researchers, and can be directly used within the FeatureCloud platform. ",
issn="2817-1705",
doi="10.2196/47652",
url="https://ai.jmir.org/2024/1/e47652",
url="https://doi.org/10.2196/47652"
}