Virginia Commonwealth University

VCU Massey Cancer Center

Automated Cancer Extraction application system

The Automated Cancer Extraction (ACE) application system was developed at VCU Massey Cancer Center for automated capture and integration of longitudinal cancer-specific data. ACE is a SQL server application that is written in C# in a .NET environment. The application has been developed to accept, parse, and integrate electronic source data from the Universal Data Store (UDS) for identifying cancer patients and relevant treatment and outcomes information maintained longitudinally. It screens those data for cancer relevance based on a cancer registrar-derived set of screening criteria including standardized codes and text search strings. All source documentation is saved and linked at the person level and is accessible for use in providing annotation to research as well as providing more accurate and complete data to the cancer registry.

ACE automates the cancer registration process, but more importantly is used in cohort discovery and comparative effectiveness research by Cancer Research Informatics and Services (CRIS) Core staff to support investigators. The cancer registry is a critical component used in support of research at Massey as it provides adjudicated and discretely stored information on diagnosis and stage for incident cancers and detailed follow up information on prevalent cancers.  These data are being integrated with UDS to supplement the structured data content of that system. Thus the ACE application serves as an essential system providing supplemental information critical to research.

The system has moved the VCU registry from a tool to obtain Commission on Cancer certification to a system useful in providing meaningful data to support research by providing a platform for capturing and integrating data to perform studies of: disparities in treatment delivery, patterns of care, and comparison of care provided across the insured and uninsured. It is used extensively for cohort discovery and population estimation to support grant proposals. ACE will be a key component to the proposed TDAAC Honest Broker system in providing necessary cancer annotation to investigators using tissue specimens.


An example of how ACE functionality has been integrated into Clinical Trials Eligibility Database (CTED) is the capture and maintenance of all treatment information in an ordered and usable format from the billing data. Consolidation of detailed treatment information has been a significant deficit in cancer surveillance data, historically limiting the usefulness of cancer registry data. Billing data represents a simple, standardized and accurate 1-8 source for capturing these data in greater detail than is required by state and Federal agencies. Thus, we have developed a process used by both ACE and CTED to automatically populate chemotherapy and radiation therapy tables (shown in Figure 4) for use in a variety of the systems and services provided by the CRIS Core. In particular, these data have been used extensively for matching against clinical trial eligibility criteria and in providing clinical annotation for TDAAC.