WebDISCO: a web service for distributed cox model learning without patient-level data sharing

Chia-Lun Lu; Shuang Wang; Zhanglong Ji; Yuan Wu; Li Xiong; Xiaoqian Jiang; Lucila Ohno-Machado

doi:10.1093/jamia/ocv083

WebDISCO: a web service for distributed cox model learning without patient-level data sharing

J Am Med Inform Assoc. 2015 Nov;22(6):1212-9. doi: 10.1093/jamia/ocv083. Epub 2015 Jul 9.

Authors

Chia-Lun Lu¹, Shuang Wang², Zhanglong Ji¹, Yuan Wu³, Li Xiong⁴, Xiaoqian Jiang⁵, Lucila Ohno-Machado¹

Affiliations

¹ Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA, 92093, USA Email: challen@ucsd.edu, shw070@ucsd.edu, z1ji@ucsd.edu, x1jiang@ucsd.edu, machado@ucsd.edu.
² Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA, 92093, USA Email: challen@ucsd.edu, shw070@ucsd.edu, z1ji@ucsd.edu, x1jiang@ucsd.edu, machado@ucsd.edu shw070@ucsd.edu x1jiang@ucsd.edu.
³ Department of Biostatistics & Bioinformatics, Duke University, Durham, NC, 27708, USA Email: yuan.wu@duke.edu.
⁴ Department of Mathematics & Computer Science, Emory University, Atlanta, GA 30322, USA. Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA, 92093, USA Email: challen@ucsd.edu, shw070@ucsd.edu, z1ji@ucsd.edu, x1jiang@ucsd.edu, machado@ucsd.edu.
⁵ Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA, 92093, USA Email: challen@ucsd.edu, shw070@ucsd.edu, z1ji@ucsd.edu, x1jiang@ucsd.edu, machado@ucsd.edu Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA, 92093, USA Email: challen@ucsd.edu, shw070@ucsd.edu, z1ji@ucsd.edu, x1jiang@ucsd.edu, machado@ucsd.edu.

Abstract

Objective: The Cox proportional hazards model is a widely used method for analyzing survival data. To achieve sufficient statistical power in a survival analysis, it usually requires a large amount of data. Data sharing across institutions could be a potential workaround for providing this added power.

Methods and materials: The authors develop a web service for distributed Cox model learning (WebDISCO), which focuses on the proof-of-concept and algorithm development for federated survival analysis. The sensitive patient-level data can be processed locally and only the less-sensitive intermediate statistics are exchanged to build a global Cox model. Mathematical derivation shows that the proposed distributed algorithm is identical to the centralized Cox model.

Results: The authors evaluated the proposed framework at the University of California, San Diego (UCSD), Emory, and Duke. The experimental results show that both distributed and centralized models result in near-identical model coefficients with differences in the range [Formula: see text] to [Formula: see text]. The results confirm the mathematical derivation and show that the implementation of the distributed model can achieve the same results as the centralized implementation.

Limitation: The proposed method serves as a proof of concept, in which a publicly available dataset was used to evaluate the performance. The authors do not intend to suggest that this method can resolve policy and engineering issues related to the federated use of institutional data, but they should serve as evidence of the technical feasibility of the proposed approach.Conclusions WebDISCO (Web-based Distributed Cox Regression Model; https://webdisco.ucsd-dbmi.org:8443/cox/) provides a proof-of-concept web service that implements a distributed algorithm to conduct distributed survival analysis without sharing patient level data.

Keywords: clinical information systems; cox model; decision support systems; distributed modeling.

Publication types

Evaluation Study
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Computer Communication Networks
Datasets as Topic
Decision Support Systems, Clinical
Humans
Information Dissemination / methods
Internet
Proportional Hazards Models*
Survival Analysis*

Abstract

Publication types

MeSH terms

Grants and funding