Bayesian Federated Inference for estimating Statistical Models based on Non-shared Multicenter Data sets

TL;DR

This paper introduces Bayesian Federated Inference (BFI), a novel approach for multicenter data analysis that improves upon federated learning by better capturing posterior distributions with fewer inference cycles, especially useful for small datasets.

Contribution

The paper develops and implements a Bayesian Federated Inference framework that enhances data sharing efficiency and accuracy over traditional federated learning in multicenter studies.

Findings

BFI captures more detailed posterior information than FL.

BFI requires only a single inference cycle across centers.

BFI performs well on both simulated and real data.

Abstract

Identifying predictive factors for an outcome of interest via a multivariable analysis is often difficult when the data set is small. Combining data from different medical centers into a single (larger) database would alleviate this problem, but is in practice challenging due to regulatory and logistic problems. Federated Learning (FL) is a machine learning approach that aims to construct from local inferences in separate data centers what would have been inferred had the data sets been merged. It seeks to harvest the statistical power of larger data sets without actually creating them. The FL strategy is not always efficient and precise. Therefore, in this paper we refine and implement an alternative Bayesian Federated Inference (BFI) framework for multicenter data with the same aim as FL. The BFI framework is designed to cope with small data sets by inferring locally not only the optimal parameter values, but also additional features of the posterior parameter distribution, capturing information beyond what is used in FL. BFI has the additional benefit that a single inference cycle across the centers is sufficient, whereas FL needs multiple cycles. We quantify the performance of the proposed methodology on simulated and real life data.