University of Pittsburgh Cancer Institute (UPCI)

Skin Cancer SPORE

Core D: Informatics Core

Michael J. Becich, MD, PhD
Melissa I. Saul, MS

Translational research has a spectrum of needs that benefit from software solutions, including clinical information annotation, data warehousing and disease modeling/analysis tools. The Informatics Core (Core D) will provide clinical research informatics services to SPORE investigators to support study design and conduct, and data collection and extraction, through the application of such informatics tools as natural language processing, machine learning, and data integration. The Informatics Core will draw heavily from the grant-funded work of Drs. Becich and Ms. Saul, who will specifically support each Project/Core as follows:

Project 1. The Informatics Core will be responsible for the data extraction and collection of clinical annotations by the Research Information Service (RIS) for the E1609 patient cohort and ensure the integration of these data into the Research Data Warehouse (RDW) deployed by the Department of Biomedical Informatics (DBMI) (i2b2, which is an open-source tool developed by Harvard) for use by the Biostatistics Core (Core C).

Project 2. The Informatics Core will assist in studying the management of the toxicities associated with the treatment for this cohort using our clinical phenotyping tool. Project 2 also relies on Core D’s Clinical Research Management System (CRMS), called the Clinical Trials Management Application (CTMA), and clinical annotation expertise provided by the RIS.

Project 3. The Informatics Core will coordinate with Drs. Zarour and Ferrone to ensure access to clinical annotation data for patients enrolled in the proposed clinical trials. With the recent addition to our RIS of collecting BRAF status, we will make these data available to the Project team as well as the Biostatistics Core. The study will also analyze the use of IFNα and we will collect this electronically from our Electronic Medical Record (EMR) systems and analyze it with cohort discovery tool. Research data generated by Project 3 will also be incorporated into our RDW.

Project 4. Ms. Saul will lead the development of algorithms to identify patients with in transit melanoma who may be eligible for enrollment in Project 4. She will also coordinate the collection of clinical annotation data from our RIS for this subset of patients.

Core A. The Informatics Core will ensure the requisite laboratory and clinical trial data are recorded, stored, backed up, and available for review and annual reporting to the Internal and External Advisory Boards and the National Cancer Institute. In addition, the Informatics Core will facilitate all data sharing within the SPORE and for intra-SPORE collaborations. The Administrative Core as well as all projects and cores will require informatics consulting and support for network storage and data sharing services. Finally, cohort discovery and data extraction support for Developmental Research and Career Development Program projects is anticipated, as phenotyping and clinical annotation services have been provided in the past and currently, including the application of advanced data collection, annotation, and standardization methods.

Core B. Ms. Saul will lead the effort to expand our ability to identify new patients who are eligible for inclusion in our biospecimen repository as well as existing patients who may have missing or incomplete information that could be extracted from our EMR system. The Informatics Core initially helped create and will continue to contribute to the management of Core B’s IMBase and StemLab databases, and will integrate that data into the RDW. Core B will be heavy users of our CTMA and RIS.

Core C. The Biostatistics Core will rely heavily on our CRMS and CTMA to support SPORE clinical trial (Projects 2, 3 and 4) data management. The Informatics Core will supply Core C with direct access to the CTMA and the RDW for data access and adverse events reporting. The Biostatistics Core will rely heavily on the Informatics Core for network storage and data sharing services.

In addition, the Informatics Core will work with SPORE investigators and the PI to ensure that the existing clinical (from EMRs) and cancer registry data are available for analysis and to develop new algorithms if required by the project. In particular, we will work with Core C as we deploy our RDW to coordinate the biostatistics analysis requirements. Informatics Core staff will ensure compliance with all security and privacy regulations with respect to data and will work with the entire SPORE team in preparing progress reports, abstracts, manuscripts, and presentations.