UMB ICTR

Before going though the data request pathway noted below, save yourself time and use TriNetX to see if your cohort of interest exists.

UMMS requires that requests to view/use patient information/data for the purpose of research go through the UMB ICTR. See How to Apply below.  In the ICTR Resource Request form, please see the Informatics section in the application and check “Access to Clinical Data”.  Also, the Epic team will want this completed document uploaded into the ICTR application  EPIC Data Request_Additional Elements

UMMS now has a strict review process when Epic data is being used for research. A few things:

• UMMS is supportive of research but strictly requires that the request is submitted through the ICTR. This includes manually abstracted data. 
• In partnership with UMMS, the UMB ICTR now tracks all requests to use Epic data for research.
• While UMMS does require IRB review/approval before data can be manually abstracted and/or released to the researcher, the IRB review/approval is not needed to initiate the request through the ICTR. The ICTR will review the request and forward to the UMMS Epic data honest broker.
• Epic data cannot leave the campus without the required approvals, such as a DUA or DTUA, which requires UMMS approval. This includes UMMS Epic data in REDCap that will be provided to an entity outside of UMB or Epic data entered into another academic center's REDCap.  
• In your IRB protocol, be clear what Epic data are being accessed, how it is accessed, who is accessing it, where it is going, etc.
• In the IRB submission, you will also need to note the variables needed. Even if the Epic data you plan to use does not include any of the HIPAA 18 identifiers (which includes dates of service/admission/discharge), the project must still go through this process.

Led by Dr. Jean Jeudy, he Clinical and Research Imaging Informatics Core (CRIC) is a resource for the UMB ICTR that aims to bridge information science, computer science, and health care imaging, delivering a comprehensive suite of services for researchers on campus.

CRIC provides a breadth of imaging-related services, including ingestion and curation of imaging data, project organization, labeling, annotation of images and data for search, and providing compliant, configurable de-identification tools.

The National Institutes of Health’s new mandatory policy on data management and sharing is intended to improve research reproducibility and leverage data for greater effectiveness. CRIC is aligned to help researchers at all funding levels comply with the new regulations.

The core offers advice and guidance on imaging informatics topics such as DICOM, medical ontologies, artificial intelligence, image post-processing, and data harmonization with common standards. Advanced custom workflows can be crafted in conjunction with the University of Maryland Medical Intelligent Imaging Center (UM2ii). Through collaboration with UM2ii, researchers can automate labeling, conversion, pre-processing, and pipelines for their projects in a secure and compliant manner.

We are passionate about providing sophisticated and robust services to the UMB scientific community and are committed to creating novel informatics solutions for single or multi-center studies.

• Access to Medicare and IQVIA data.  Researchers interested in Medicare and IQVIA data may be eligible for ICTR Voucher Support to help defray the cost (see ... below).  For full description, see PHSR Community Database Description of Databases and PHSR Community Database Fees. 
  • Medicare Chronic Conditions Warehouse (CCW) 5% Sample
  • Medicare Current Beneficiary Survey (MCBS)
  • IQVIA (IMS Health Pharmetrics Plus) 10% Sample
• Assistance with securing Memorandums of Understanding or Data Use Agreements.

• Patient-centered PHR/patient portal implementation
• Web-based research and usability testing
• Hospital information systems evaluation and implementation

• Use of digital technology in support of health, such as mobile apps
• Use of eHealth/mHealth/patient portal interventions to promote and manage the health of adults age 50 and older

• The REDCap team can help build a database for your project in .  Please be prepared to provide your current, IRB-approved research surveys, data entry /case report forms, and your project's data collection schedule.    Data collected are stored and maintained locally on campus in a firewalled server managed by the UMB. REDCap provides automated export procedures for seamless data downloads to Excel, PDF, and common statistical packages (SPSS, SAS, Stata, R) as well as a built-in project calendar, a scheduling module, ad hoc reporting tools, and advanced features, such as auto-validation, branching logic, file uploading, calculated fields, and survey stop actions.  REDCap can be set up for multi-center studies as well. 

More information about REDCap can be found here Data Management here REDCap.

The University of Maryland Baltimore County (UMBC) provides Artificial Intelligence, Machine Learning, & Cybersecurity Services to the UMB ICTR Informatics Core.  The new UMBC services will be an exciting addition for those researchers exploring the use of machine learning (ML) and Artificial Intelligence (AI) to identify patterns in data and make decisions with minimal human intervention.   For researchers interested in developing apps and devices that may improve delivery and exchange of health information, UMBC's Cybersecurity expertise will help the researcher protect those devices, systems, and data from attack.  See below for a list of UMBC Core services available to UMB researchers.

UMBC - ICTR Core Capabilities

• Securing medical devices
• Securing smart systems, e.g., smart surgery rooms
• Protecting learned/predictive models from attacks
• Deep learning and artificial neural networks
• Natural language processing
• Graph analytics
• Time series analytics
• Data visualization augmented reality and virtual reality

UMBC - ICTR Core Example of Services:

• Consult to uncover possible cybersecurity risks associated with devices and/or systems.
• Consult on ways to protect devices and/or systems from attackers, either at design time or after deployment.
• Consult on ways to apply artificial intelligence and machine learning to solve specific problems given existing data, including processing pipelines, specific algorithms, and evaluation methodology
• Advise on what additional data could be collected or obtained to potentially improve the utility of AI/ML for specific use cases.
• Construct simple proof-of-concept AI/ML systems to understand what level of performance might be achieved with more time, data, or resources
• Advise on the best visual representations to explore complex datasets and to communicate results to others.