Research Capabilities of Linked Datasets (RCOLD)
Project Details
This project will supplement the first large-scale, comprehensive data linkage that links primary care and hospital data for cancer patients under the Victorian Comprehensive Cancer Centre’s Data-Driven Research Program.
Patron ID: PAT012/PAT019/PAT1033
Project Lead:
This project represents the first large-scale, primary care and hospital data linkage for cancer patients under the Victorian Comprehensive Cancer Centre’s Data Connect Program. This project includes the large-scale primary care data source MedicineInsight data set linked to the statutory reporting data sets from four major metropolitan health services admitted, outpatient and emergency data sets.
This linkage allows analysis and research feasibility using linked cancer patient data at the three key points where the primary care and hospital systems intersect during a patient’s cancer journey (pre-diagnosis, during active treatment and during post-treatment follow-up) when lack of integration between healthcare sectors in likely to result in less than optimal patient outcomes. Inclusion of the Patron data set complements existing linkages and allow for an extension of analyses between the primary and acute patient cohorts, further enhancing analytical capability for the purpose of health services research with the aim of improving clinical care across the health services continuum.
Sub Projects:
PAT1033_2 ‘Feasibility analysis for research concepts’.
Exploring the hospital and linked Patron & MedicineInsight datasets to assess the feasibility of cancer research proposals on behalf of the Data Connect team and external researchers.
Project Lead: Alex Lee
PAT1033_3 ‘Patterns of diagnostic testing for OG cancer related symptoms including cost analysis of testing’.
Symptoms associated with cancer, referred to as 'cancer symptoms,' often share characteristics with non-cancer conditions commonly seen in general practice. The diversity of potential diagnoses in primary care, combined with low cancer prevalence, can result in significant testing variations, the full extent and implications of which remain unclear. This project aims to enhance our understanding of diagnostic testing patterns for common upper gastrointestinal symptoms associated with oesophagogastric cancer in Victorian general practice. Project Lead: Jon Emery
PAT1033_4 ‘Weight loss as an early indication of cancer’.
This project is a replication study of a UK diagnostic accuracy that aimed to calculate the six month risk of cancer in primary care patients with unexplained weight loss (UWL). For our study we first derive a cohort of patients with unexplained weight loss and include relevant blood tests and weight measurements. We then use the cancer registry data to identify the proportion of patients who are diagnosed with cancer within six months of first presenting with UWL.
Project Lead: Jon Emery
PAT1033_5 ‘Machine Learning methods for cancer risk prediction of upper gastro-intestinal cancers’.
This project aims to develop machine learning and advanced statistical methods for the prediction of upper gastro-intestinal (GI) cancers in Australian primary care patients. We will start by reviewing existing literature on risk prediction methodologies that use machine learning models applied to electronic health records data sources and identify which are best suited to our data. The primary care data in PATRON is extremely rich but in most studies, usually only a small subset of information is used to carry out predictive analyses, for example specific blood tests or given symptoms. Furthermore, these analyses are often done using information at a single point in time to make predictions. In this project we aim to make more complete use of the trends in clinical information in the lead up to a cancer diagnosis in order to improve on existing approaches to risk prediction for upper GI cancers. A secondary outcome of this study will therefore be to provide further evidence on the suitability of machine learning for risk prediction using electronic health records.
Research Publications
- Alex Lee, Damien McCarthy, Rebecca J Bergin, Allison Drosdowsky, Javiera Martinez Gutierrez, Chris Kearney, Sally Philip, Meena Rafiq, Brent Venning, Olivia Wawryk, Jianrong Zhang, Jon Emery, Data Resource Profile: Victorian Comprehensive Cancer Centre Data Connect, International Journal of Epidemiology, Volume 52, Issue 6, December 2023, Pages e292–e300
- Primary care patients presenting with unexpected weight loss in Australian general practices: replication of a diagnostic accuracy study https://pubmed.ncbi.nlm.nih.gov/40730405/
- Lee A, de Mendonca L, McCarthy D, Nelson C, Rafiq M, Venning B, Chima S, Daly D, Fishman G, Kearney C, Hunter B, Lim FS, Manski-Nankervis JA, Nicholson BD, Emery J, Martinez-Gutierrez J. Primary care patients presenting with unexpected weight loss in Australian general practices: replication of a diagnostic accuracy study. BMJ Open. 2025 Jul 28;15(7):e104690. https://doi.org/10.1136/bmjopen-2025-104690