SurvMaximin: Robust Federated Approach to Transporting Survival Risk Prediction Models

Abstract

Objective: For 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 Methods: For 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. Results: Simulation 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. Conclusions: The 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.

Hospitalizations Associated With Mental Health Conditions Among Adolescents in the US and France During the COVID-19 Pandemic

“…The 4CE network leverages a multisite research infrastructure based on routinely collected health care data to perform COVID-19–related clinical analyses expeditiously and at scale while preserving patient confidentiality . While the focus to date has been on COVID-19, the contemporaneous efforts on methods development, ongoing addition of new hospital sites across health care systems, and open-source release of all code has produced a robust infrastructure that supports ongoing collaborative research studies on diverse topics . In particular, the 4CE infrastructure will be able to support continued monitoring of health care utilization for mental health conditions among adolescents, including assessing trends in specific conditions and identifying patient groups at greatest risk for mental health disorders.…”

Comparison of different prognostic scores in estimating short- and long-term mortality in COVID-19 patients above 60 years old in a university hospital in Belgium

“…Age is often reviewed as an important risk factor for a higher mortality in COVID-19 [16,17], and even though we only looked at a population older than 60 years old, we still withheld a significant difference in age between the survivors and the deceased. It is also well known that renal function and COVID-19 infection was associated with a higher mortality [19,20]. These 3 criteria were not included in CFS, NEWS, qCSI or qSOFA.…”