Advancing interpretable regression analysis for binary data: A novel distributed algorithm approach
Tong, J; Li, L; Reps, JM; et al., Statistics in Medicine
Published
December 2024
Journal
Statistics in Medicine
Abstract
Sparse data bias, where there is a lack of sufficient cases, is a common problem in data analysis, particularly when studying rare binary outcomes. Although a two-step meta-analysis approach may be used to lessen the bias by combining the summary statistics to increase the number of cases from multiple studies, this method does not completely eliminate bias in effect estimation. In this paper, we propose a one-shot distributed algorithm for estimating relative risk using a modified Poisson regression for binary data, named ODAP-B. We evaluate the performance of our method through both simulation studies and real-world case analyses of postacute sequelae of SARS-CoV-2 infection in children using data from 184,501 children across eight national academic medical centers. Compared with the meta-analysis method, our method provides closer estimates of the relative risk for all outcomes considered including syndromic and systemic outcomes. Our method is communication-efficient and privacy-preserving, requiring only aggregated data to obtain relatively unbiased effect estimates compared with two-step meta-analysis methods. Overall, ODAP-B is an effective distributed learning algorithm for Poisson regression to study rare binary outcomes. The method provides inference on adjusted relative risk with a robust variance estimator.
Authors
Jiayi Tong, Lu Li, Jenna Marie Reps, Vitaly Lorman, Naimin Jing, Mackenzie Edmondson, Xiwei Lou, Ravi Jhaveri, Kelly J Kelleher, Nathan M Pajor, Christopher B Forrest, Jiang Bian, Haitao Chu, Yong Chen
Keywords
binary data; distributed algorithm; modified Poisson regression; relative risk
Short Summary
This RECOVER study focused on a problem that happens when scientists study rare events. When scientists have very few cases of rare events to study, the usual ways of studying data can give misleading results. One way to fix this is to combine data from many hospitals or clinics so there are more cases to study. But, sharing detailed patient information raises concerns about privacy, so patient privacy must be protected when combining data from multiple healthcare centers.
In this study, RECOVER researchers created a new tool called ODAP-B, which combines information more accurately without sharing patient details. This is because it only needs a summary of patient data, not full health records. By using ODAP-B, researchers can better understand what increases the chance of a rare event happening while protecting patient privacy.