SurvMaximin: Robust Federated Approach to Transporting Survival Risk Prediction Models (preprint)

ObjectiveFor multi-center heterogeneous Real-World Data (RWD) with time-to-event outcomes and high-dimensional features, we propose the SurvMaximin algorithm to estimate Cox model feature coefficients for a target population by borrowing summary information from a set of health care centers without sharing patient-level information. Materials and MethodsFor each of the centers from which we want to borrow information to improve the prediction performance for the target population, a penalized Cox model is fitted to estimate feature coefficients for the center. Using estimated feature coefficients and the covariance matrix of the target population, we then obtain a SurvMaximin estimated set of feature coefficients for the target population. The target population can be an entire cohort comprised of all centers, corresponding to federated learning, or can be a single center, corresponding to transfer learning. ResultsSimulation studies and a real-world international electronic health records application study, with 15 participating health care centers across three countries (France, Germany, and the U.S.), show that the proposed SurvMaximin algorithm achieves comparable or higher accuracy compared with the estimator using only the information of the target site and other existing methods. The SurvMaximin estimator is robust to variations in sample sizes and estimated feature coefficients between centers, which amounts to significantly improved estimates for target sites with fewer observations. ConclusionsThe SurvMaximin method is well suited for both federated and transfer learning in the high-dimensional survival analysis setting. SurvMaximin only requires a one-time summary information exchange from participating centers. Estimated regression vectors can be very heterogeneous. SurvMaximin provides robust Cox feature coefficient estimates without outcome information in the target population and is privacy-preserving.

Federated Adaptive Causal Estimation (FACE) of Target Treatment Effects (preprint)

Federated learning of causal estimands may greatly improve estimation efficiency by leveraging data from multiple study sites, but robustness to heterogeneity and model misspecifications is vital for ensuring validity. We develop a Federated Adaptive Causal Estimation (FACE) framework to incorporate heterogeneous data from multiple sites to provide treatment effect estimation and inference for a flexibly specified target population of interest. FACE accounts for site-level heterogeneity in the distribution of covariates through density ratio weighting. To safely incorporate source sites and avoid negative transfer, we introduce an adaptive weighting procedure via a penalized regression, which achieves both consistency and optimal efficiency. Our strategy is communication-efficient and privacy-preserving, allowing participating sites to share summary statistics only once with other sites. We conduct both theoretical and numerical evaluations of FACE and apply it to conduct a comparative effectiveness study of BNT162b2 (Pfizer) and mRNA-1273 (Moderna) vaccines on COVID-19 outcomes in U.S. veterans using electronic health records from five VA regional sites. We show that compared to traditional methods, FACE meaningfully increases the precision of treatment effect estimates, with reductions in standard errors ranging from $26\%$ to $67\%$.

An efficient distributed algorithm with application to COVID-19 data from heterogeneous clinical sites (preprint)

ObjectivesIntegrating electronic health records (EHR) data from several clinical sites offers great opportunities to improve estimation with a more general population compared to analyses based on a single clinical site. However, sharing patient-level data across sites is practically challenging due to concerns about maintaining patient privacy. The objective of this study is to develop a novel distributed algorithm to integrate heterogeneous EHR data from multiple clinical sites without sharing patient-level data. Materials and MethodsThe proposed distributed algorithm for binary regression can effectively account for between-site heterogeneity and is communication-efficient. Our method is built on a pairwise likelihood function in the extended Mantel-Haenszel regression, which is known to be statistically highly efficient. We construct a surrogate pairwise likelihood function through approximating the target pairwise likelihood by its surrogate. We show that the proposed surrogate pairwise likelihood leads to a consistent and asymptotically normal estimator by effective communication without sharing individual patient-level data. We study the empirical performance of the proposed method through a systematic simulation study and an application with data of 14,215 COVID-19 patients from 230 clinical sites at UnitedHealth Group Clinical Research Database. ResultsThe proposed method was shown to perform close to the gold standard approach under extensive simulation settings. When the event rate is <5%, the relative bias of the proposed estimator is 30% smaller than that of the meta-analysis estimator. The proposed method retained high accuracy across different sample sizes and event rates compared with meta-analysis. In the data evaluation, the proposed estimate has a relative bias <9% when the event rate is <1%, whereas the meta-analysis estimate has a relative bias at least 10% higher than that of the proposed method. ConclusionsOur simulation study and data application demonstrate that the proposed distributed algorithm provides an estimator that is robust to heterogeneity in event rates when effectively integrating data from multiple clinical sites. Our algorithm is therefore an effective alternative to both meta-analysis and existing distributed algorithms for modeling heterogeneous multi-site binary outcomes.

Lossless Distributed Linear Mixed Model with Application to Integration of Heterogeneous Healthcare Data (preprint)

Linear mixed models (LMMs) are commonly used in many areas including epidemiology for analyzing multi-site data with heterogeneous site-specific random effects. However, due to the regulation of protecting patients’ privacy, sensitive individual patient data (IPD) are usually not allowed to be shared across sites. In this paper we propose a novel algorithm for distributed linear mixed models (DLMMs). Our proposed DLMM algorithm can achieve exactly the same results as if we had pooled IPD from all sites, hence the lossless property. The DLMM algorithm requires each site to contribute some aggregated data (AD) in only one iteration. We apply the proposed DLMM algorithm to analyze the association of length of stay of COVID-19 hospitalization with demographic and clinical characteristics using the administrative claims database from the UnitedHealth Group Clinical Research Database.