Title | An adaptive federated learning framework for clinical risk prediction with electronic health records from multiple hospitals. |
Publication Type | Journal Article |
Year of Publication | 2024 |
Authors | Pan W, Xu Z, Rajendran S, Wang F |
Journal | Patterns (N Y) |
Volume | 5 |
Issue | 1 |
Pagination | 100898 |
Date Published | 2024 Jan 12 |
ISSN | 2666-3899 |
Abstract | Clinical risk prediction with electronic health records (EHR) using machine learning has attracted lots of attentions in recent years, where one of the key challenges is how to protect data privacy. Federated learning (FL) provides a promising framework for building predictive models by leveraging the data from multiple institutions without sharing them. However, data distribution drift across different institutions greatly impacts the performance of FL. In this paper, an adaptive FL framework was proposed to address this challenge. Our framework separated the input features into stable, domain-specific, and conditional-irrelevant parts according to their relationships to clinical outcomes. We evaluate this framework on the tasks of predicting the onset risk of sepsis and acute kidney injury (AKI) for patients in the intensive care unit (ICU) from multiple clinical institutions. The results showed that our framework can achieve better prediction performance compared with existing FL baselines and provide reasonable feature interpretations. |
DOI | 10.1016/j.patter.2023.100898 |
Alternate Journal | Patterns (N Y) |
PubMed ID | 38264713 |
PubMed Central ID | PMC10801228 |
Grant List | RF1 AG084178 / AG / NIA NIH HHS / United States R01 AG080624 / AG / NIA NIH HHS / United States T32 GM083937 / GM / NIGMS NIH HHS / United States R01 AG080991 / AG / NIA NIH HHS / United States RF1 AG072449 / AG / NIA NIH HHS / United States R01 AG076234 / AG / NIA NIH HHS / United States R01 MH124740 / MH / NIMH NIH HHS / United States |
An adaptive federated learning framework for clinical risk prediction with electronic health records from multiple hospitals.
Submitted by chz4003 on September 2, 2024 - 2:51pm
Division:
Institute of Artificial Intelligence for Digital Health
Category:
Faculty Publication