Real-World Data

About Real-World Data

NCI’s Real-World Data (RWD) Program enables cancer researchers like you to understand patient experiences in real-world clinical settings. The program does this by focusing on improving the quality, completeness, and collection of patient data from the Electronic Health Record (EHR) collected during routine clinical care.

RWD differs from other research data because RWD isn’t limited to patients enrolled in clinical trials. RWD can also uncover inconsistencies in research data in our communities. By collecting and analyzing this data, we can transform it into Real-World Evidence (RWE), which offers critical insights into patient outcomes and healthcare practices.

One of the largest sources of RWD is the EHR, which includes clinical data about the patient. Today, however, RWD in many EHRs is messy. Clinical care teams capture similar values in different ways and record them in different parts of the EHR. For example, someone may record a lab test order in one table of the EHR and the lab test value in a different table in the EHR.

NCI’s RWD Program provides leadership in developing the standards for data exchange. The goals of the program are to:

1. identify essential components for integrating RWD into institutional ecosystems (i.e., infrastructure, data, people, institutional support).
2. develop data extraction and transformation guidelines.
3. create machine learning (ML) and artificial intelligence (AI) tools for data conformance, distribution, and completeness verification.
4. organize expert panels on EHR/ Fast Healthcare Interoperability Resources (FHIR) data extraction and harmonization.
5. develop and validate computable phenotype guidelines.

In 2023, the NCI RWD Program launched an administrative supplement program. This program had three aims:

1. Develop AI methods/tools that you can use to rapidly assess the completeness and quality of EHR data.
2. Use Large (or Medium) Language Models to assist you with the extraction of diagnosis, treatment, and other relevant data from unstructured clinical and pathology reports.
3. Establish a privacy-preserving federated learning network where you and other researchers can run multi-modal, ML models using clinical, genomic, and imaging data, among others.

NCI’s Role

One of the early efforts of NCI’s RWD Program is its partnership with the Assistant Secretary for Technology Policy and Office of the National Coordinator for Health Information Technology (ASTP/ ONC) and the USCDI+ Cancer Program. The goal of the USCDI+ Cancer Program is to accelerate research by defining a core set of cancer research-specific data concepts that you can easily exchange and harmonize across institutions. NCI and ONC co-lead this endeavor with input from the Centers for Medicare & Medicaid Services, the Centers for Disease Control and Prevention, and the U.S. Food and Drug Administration.

Additionally, NCI CBIIT staff and researchers are part of the USCDI+ Cancer Team, which creates implementation guides. If you’re part of an academic institution or industry partner, you can use these guides to learn how to implement and exchange data concepts.

Connecting the Cancer Community

USCDI+ Cancer published the USCDI+ Cancer Registry draft data element list, which is the minimum necessary data set to identify and extract data and support data sharing and linkage approaches. If you’d like to review and provide feedback on this list, follow the instructions below:

• Visit the USCDI+ platform.
• Create an account.
• Review the draft cancer registry data element list.
• Submit your comments and suggestions through the form.

You can also watch session recordings and download PowerPoint slides from the recent Cancer Research Data Exchange Summit, which CBIIT and ONC organized as part of USCDI+ Cancer.

Additional Information

If you have questions or want more information about NCI’s RWD Program, email Dr. Shannon Silkensen and/or NCIClinicalInformatics@nih.gov.