WICOX: Weight-Based Integrated Cox Model for Time-to-Event Data in Distributed Databases Without Data-Sharing
- 1 November 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (1) , 526-537
Abstract
To exploit large-scale biomedical data, the application of common data models and the establishment of data networks are being actively carried out worldwide. However, due to the privacy issues, it is difficult to share data distributed among institutions. In this study, we developed and evaluated weight-based integrated Cox model (WICOX) as a privacy-protecting method without sharing patient-level information across institutions. WICOX generates a weight for each institutional model and builds an integrated model of multi-institutional data based on these weights. WICOX does not require iterative communication until the centralized parameter converges. We performed experiments to show the weight characteristic of our algorithm based on 10 hospitals (2910 intensive care unit (ICU) stays in total) from the electronic intensive care unit Collaborative Research Database to predict time to ICU mortality with eight risk factors. Compared with the centralized Cox model, WICOX showed biases from 0 to 0.68E-2, from 0.00E-2 to 4.98E-2, and from 0.74E-2 to 1.7E-2 for time-dependent AUC, log hazard ratio, and survival rate, respectively. In addition, through simulation results using real 10 hospitals, WICOX showed robust results in accuracy under any composition of hospitals. The results of the experiments highlight that WICOX has robust characteristics and provides predictive performance and statistical inference results nearly the same as those of the centralized model. WICOX is a non-iterative method using the weight of institutional model for implementing the Cox model across multiple institutions in a privacy-preserving manner.Keywords
Funding Information
- Bio-Industrial Technology Development Program (20014841)
- Ministry of Trade, Industry and Energy
- Korea Institute of Drug Safety and Risk Management
- Korea Health Technology R&D Project
- Korea Health Industry Development Institute
- Ministry of Health & Welfare, Republic of Korea (HI19C1330)
This publication has 32 references indexed in Scilit:
- Grid multi-category response logistic modelsBMC Medical Informatics and Decision Making, 2015
- Electronic clinical laboratory test results data tables: lessons from Mini‐SentinelPharmacoepidemiology and Drug Safety, 2014
- Grid Binary LOgistic REgression (GLORE): building shared models without sharing dataJournal of the American Medical Informatics Association, 2012
- Design considerations, architecture, and use of the Mini‐Sentinel distributed data systemPharmacoepidemiology and Drug Safety, 2012
- Relaxing the Rule of Ten Events per Variable in Logistic and Cox RegressionAmerican Journal of Epidemiology, 2006
- Human Resource Information Systems2003
- Generalisation and extrapolationBMJ, 1998
- Selection bias in observational and experimental studiesStatistics in Medicine, 1994
- Maximum Likelihood Techniques: An Overview1994
- Meta-analysis in clinical trialsControlled Clinical Trials, 1986