ODAL: A one-shot distributed algorithm to perform logistic regressions on electronic health records data from multiple clinical sites

Abstract

Electronic Health Records (EHR) contain extensive information on various health outcomes and risk factors, and therefore have been broadly used in healthcare research. Integrating EHR data from multiple clinical sites can accelerate knowledge discovery and risk prediction by providing a larger sample size in a more general population which potentially reduces clinical bias and improves estimation and prediction accuracy. To overcome the barrier of patient-level data sharing, distributed algorithms are developed to conduct statistical analyses across multiple sites through sharing only aggregated information. The current distributed algorithm often requires iterative information evaluation and transferring across sites, which can potentially lead to a high communication cost in practical settings. In this study, we propose a privacy-preserving and communication-efficient distributed algorithm for logistic regression without requiring iterative communications across sites. Our simulation study showed our algorithm reached comparative accuracy comparing to the oracle estimator where data are pooled together. We applied our algorithm to an EHR data from the University of Pennsylvania health system to evaluate the risks of fetal loss due to various medication exposures.

Robust-ODAL: Learning from heterogeneous health systems without sharing patient-level data

“…However, a challenge for such data integration is that the identification of which sites belonging to the majority of sites is unknown. To handle this type of heterogeneity and keep the algorithm to be entirely data-driven, we propose the following distributed algorithm by strengthening the algorithm in Duan et al (2019) [20].…”

“…To this end, in this paper, we attempt to develop a simple yet effective privacy-preserving distributed algorithm for fitting logistic regression within heterogeneous health systems without sharing patient-level data. The key idea is to modify the ODAL algorithm [20] by communicating robust summary statistics that are less sensitive to the existence of “outlying studies”. Through simulation studies and real data analysis using databases from the Janssen Research, we found that our new algorithm, which we refer to as the “robust-ODAL” method, is substantially more robust to the outlying studies and produces less biased estimates than the current ODAL method and traditional meta-analysis method.…”

Leverage Real-world Longitudinal Data in Large Clinical Research Networks for Alzheimer’s Disease and Related Dementia (ADRD)

“…The stateof-the-art method for multicenter study, without sharing patient-level information, is the meta-analysis, where each site fits separate analysis and all local estimates are synthesized using a weighted average 15 . In addition to metaanalysis, several distributed learning algorithms, in which only aggregate information is allowed to be shared across institutions, have been developed to overcome the privacy issue in a clinical research network [16][17][18][19] . Among the existing methods, Duan et al 20 .…”

Exploring the Feasibility of Using Real-World Data from a Large Clinical Data Research Network to Simulate Clinical Trials of Alzheimer’s Disease

“…In multicenter studies, sharing data is a major challenge due to privacy concerns 16 . To circumvent the issue of sharing individual patient-level data, many distributed algorithms have been developed to jointly study multiple datasets by communicating only summary-level statistics [17][18][19][20] . Among them, Duan et al [19][20] proposed a privacy-preserving Oneshot Distributed Algorithm for Logistic regression (ODAL), which can be used to identify risk factors of a binary healthcare outcome of interest.…”

“…To circumvent the issue of sharing individual patient-level data, many distributed algorithms have been developed to jointly study multiple datasets by communicating only summary-level statistics [17][18][19][20] . Among them, Duan et al [19][20] proposed a privacy-preserving Oneshot Distributed Algorithm for Logistic regression (ODAL), which can be used to identify risk factors of a binary healthcare outcome of interest. Compared to existing methods, ODAL requires only one round of communication across sites and can achieve high accuracy as a pooled analysis in which a logistic regression is fitted on the combined dataset 20 .…”