tsungtingkuo / glorechain

Fair compute loads enabled by blockchain: sharing models by alternating client and server roles

Fair compute loads enabled by blockchain: sharing models by alternating client and server roles

Citation

Please cite as below:

• Tsung-Ting Kuo, Rodney A. Gabriel, and Lucila Ohno-Machado, "Fair compute loads enabled by blockchain: sharing models by alternating client and server roles." Journal of the American Medical Informatics Association (JAMIA). 2019. doi: 10.1093/jamia/ocy180.

• Tsung-Ting Kuo, Rodney A. Gabriel, & Lucila Ohno-Machado. (2024). tsungtingkuo/explorerchain v1.0.0 (v1.0.0). Zenodo. doi: 10.5281/zenodo.11508611.

Introduction

This is the code for the GloreChain, which runs privacy-preserving batch predictive modeling algorithm on a permissioned blockchain network.

Predictive Model

GloreChain is based on GLORE modeling method.

Example Data

The two sets of example data (Edin and CA) are derived from the two datasets included in EXPLORER.

Required Components

1. Prerequisites
   • Ubuntu (64-bit 14.04 with superuser privilege)
   • Java (1.8 or later)
2. Libraries
   • Apache Common Math v1.2
   • AUC Calculator v0.2
   • JAMA v1.0.2
   • JSON.simple v1.1.1
   • Tsung-Ting's Java Utilities v1.0.0
3. Blockchain Platform
   • MultiChain v1.0 alpha 27

Acknowledgement

This work is partly funded by U.S. National Institutes of Health (K99/R00HG009680 and R01GM118609). The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the software.

Contact

Thank you for using our software. If you have any questions or suggestions, please kindly contact Tsung-Ting Kuo ([e-mail]), UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, USA.

DOI