Federated Diabetes Prediction in Canadian Adults Using Real-world Cross-Province Primary Care Data

TL;DR

This study introduces a federated learning approach for diabetes prediction using real-world Canadian primary care data, achieving comparable or better accuracy than centralized models while preserving patient privacy.

Contribution

First application of federated learning for diabetes prediction in Canadian clinical data, addressing privacy concerns and demonstrating its effectiveness compared to centralized models.

Findings

Federated MLP achieved similar or higher performance than centralized models.

Federated logistic regression performed worse than centralized logistic regression.

Addressed class imbalance with downsampling techniques.

Abstract

Integrating Electronic Health Records (EHR) and the application of machine learning present opportunities for enhancing the accuracy and accessibility of data-driven diabetes prediction. In particular, developing data-driven machine learning models can provide early identification of patients with high risk for diabetes, potentially leading to more effective therapeutic strategies and reduced healthcare costs. However, regulation restrictions create barriers to developing centralized predictive models. This paper addresses the challenges by introducing a federated learning approach, which amalgamates predictive models without centralized data storage and processing, thus avoiding privacy issues. This marks the first application of federated learning to predict diabetes using real clinical datasets in Canada extracted from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) without crossprovince patient data sharing. We address class-imbalance issues through downsampling techniques and compare federated learning performance against province-based and centralized models. Experimental results show that the federated MLP model presents a similar or higher performance compared to the model trained with the centralized approach. However, the federated logistic regression model showed inferior performance compared to its centralized peer.