Comparing Federated Stochastic Gradient Descent and Federated Averaging for Predicting Hospital Length of Stay

TL;DR

This paper compares FedSGD and FedAVG algorithms for federated learning to predict hospital length of stay, demonstrating privacy-preserving, accurate, collaborative modeling across hospitals.

Contribution

It introduces a graph-based federated learning framework for hospital LOS prediction and compares two optimization algorithms in this context.

Findings

Federated learning achieves accurate LOS prediction while preserving privacy.

FedAVG outperforms FedSGD in convergence speed and accuracy.

The graph modeling approach effectively facilitates decentralized data collaboration.

Abstract

Predicting hospital length of stay (LOS) reliably is an essential need for efficient resource allocation at hospitals. Traditional predictive modeling tools frequently have difficulty acquiring sufficient and diverse data because healthcare institutions have privacy rules in place. In our study, we modeled this problem as an empirical graph where nodes are the hospitals. This modeling approach facilitates collaborative model training by modeling decentralized data sources from different hospitals without extracting sensitive data outside of hospitals. A local model is trained on a node (hospital) by aiming the generalized total variation minimization (GTVMin). Moreover, we implemented and compared two different federated learning optimization algorithms named federated stochastic gradient descent (FedSGD) and federated averaging (FedAVG). Our results show that federated learning enables accurate prediction of hospital LOS while addressing privacy concerns without extracting data outside healthcare institutions.