International health data harmonisation and benchmarking to support research across the continuum of care

Project Status
Current

Chief Investigator
Siaw-Teng Liaw

Project Team
Chitta Baral (Arizona State University), Simon de Lusignan (University of Surrey), Mark Harris, Louisa Jorm (UNSW), Michael Kahn (University of Colorado), Nigel Lovell (UNSW Biomedical Engineering)

Research Staff
Jitendra Jonnagaddala, Guan Guo, Kha Vo

Medical Student
Sanjay Farshid, Su Lin Yeoh, Mike Wu, Elizabeth Qian

Background

The UNSW ePBRN has developed a data repository of linked pseudonymised patients derived from electronic health records of general practices and hospitals in an integrated health neighbourhood in SW Sydney. The Observational Health Data Science Informatics (OHDSI) community is an established international network of researchers and observational health databases with a central coordinating center housed at Columbia University (www.ohdsi.org). The Observational Medical Outcomes Program (OMOP) Common Data Model is central to OHDSI. 

Objective

This project mapped observational data from the ePBRN dataset to similar data sets in the international EHR-derived datasets through the OMOP Common Data Model.

Publications

  1. Liyanage H, Liaw ST, Jonnagaddala J, de Lusignan S. Common Data Models (CDMs) to enhance Big Data Analytics: A Diabetes Use Case to Compare Three CDMs. Stud Health Tech & Informatics 2018; 255: 60-64.
  2. Farshid S, Jonnagaddala J, Guan G, Wu M, Liaw ST. (2018). Harmonising primary care data using international standard vocabularies for observational research. Zenodo. http://doi.org/10.5281/zenodo.2538863
  3. Kha A, Jonnagaddala J, Liaw ST. Supervised meta-ensemble algorithm for data linkage (under revision – J Biomedical Informatics)
  4. Guo G, Jonnagaddala J, Liaw ST. Cohort Selection for Clinical Trials Using Multiple Instance Learning (under review - JAMIA)