Learning from local to global: An efficient distributed algorithm for modeling time-to-event data

• Type of Material: Article
• Authors: Rui Duan, University of Pennsylvania; Chongliang Luo, University of Pennsylvania; Martin J Schuemie, Janssen Res & Dev LLC; Jiayi Tong, University of Pennsylvania; Jason Liang, National Institute of Allergy and Infectious Diseases; Howard Chang, Emory University; Mary Regina Boland, University of Pennsylvania; Jiang Bian, University of Florida; Hua Xu, Univ Texas Hlth Sci Ctr Houston; John H Holmes, University of Pennsylvania; Christopher B Forrest, Childrens Hospital of Philadelphia; Sally C Morton, Virginia Polytechnic Institute & State University; Jesse A Berlin, Johnson & Johnson; Jason H Moore, University of Pennsylvania; Kevin B Mahoney, University of Pennsylvania; Yong Chen, University of Pennsylvania
• Language: English
• Date: 2020-07-01
• Publisher: OXFORD UNIV PRESS
• Publication Version: Final Published Version
• Copyright Statement: © The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: [e-mail]
• Final Published Version (URL): http://dx.doi.org/10.1093/jamia/ocaa044
• Title of Journal or Parent Work: JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
• Volume: 27
• Issue: 7
• Start Page: 1028
• End Page: 1036
• Grant/Funding Information: This work was supported in part by the National Institutes of Health grants 1R01LM012607, 1R01AI130460, 5R01LM010098, UL1TR001427, R21AG061431, R01CA246418, and 1R01AI116794, a grant from the Patient-Centered Outcomes Research Institute (PCORI) for the PEDSnet Clinical Research Infrastructure (RI-CRN-2020-007), and the Cancer Informatics and eHealth Core program at the University of Florida Health Cancer Center.
• Keywords: Computer Science, Interdisciplinary Applications; Science & Technology; meta-analysis; MYOCARDIAL-INFARCTION; Health Care Sciences & Services; RISK-FACTORS; Technology; Life Sciences & Biomedicine; PEDSNET; Cox proportional hazards model; Medical Informatics; electronic health record; data integration; Information Science & Library Science; Computer Science, Information Systems; distributed algorithm; Computer Science
• Research Categories: Statistics; Health Sciences, Epidemiology; Biology, Biostatistics

Abstract

Objective: We developed and evaluated a privacy-preserving One-shot Distributed Algorithm to fit a multicenter Cox proportional hazards model (ODAC) without sharing patient-level information across sites. Materials and Methods: Using patient-level data from a single site combined with only aggregated information from other sites, we constructed a surrogate likelihood function, approximating the Cox partial likelihood function obtained using patient-level data from all sites. By maximizing the surrogate likelihood function, each site obtained a local estimate of the model parameter, and the ODAC estimator was constructed as a weighted average of all the local estimates. We evaluated the performance of ODAC with (1) a simulation study and (2) a real-world use case study using 4 datasets from the Observational Health Data Sciences and Informatics network. Results: On the one hand, our simulation study showed that ODAC provided estimates nearly the same as the estimator obtained by analyzing, in a single dataset, the combined patient-level data from all sites (ie, the pooled estimator). The relative bias was <0.1% across all scenarios. The accuracy of ODAC remained high across different sample sizes and event rates. On the other hand, the meta-analysis estimator, which was obtained by the inverse variance weighted average of the site-specific estimates, had substantial bias when the event rate is <5%, with the relative bias reaching 20% when the event rate is 1%. In the Observational Health Data Sciences and Informatics network application, the ODAC estimates have a relative bias <5% for 15 out of 16 log hazard ratios, whereas the meta-analysis estimates had substantially higher bias than ODAC. Conclusions: ODAC is a privacy-preserving and noniterative method for implementing time-to-event analyses across multiple sites. It provides estimates on par with the pooled estimator and substantially outperforms the meta-analysis estimator when the event is uncommon, making it extremely suitable for studying rare events and diseases in a distributed manner.