The Big Data Scientist Training Enhancement Program (BD-STEP): Developing the Next Generation of Healthcare Data Scientists
The Big Data Scientist Training Enhancement Program (BD-STEP) is a fellowship program that uses data science to advance research and patient care. The Department of Veterans Affairs (VA)Veterans Health Administration (VHA) advanced fellowship launched in 2015 in collaboration with the National Cancer Institute (NCI). The program provides well-rounded training and unparalleled access to VA data resources and NCI cancer research expertise.
VHA is America’s largest integrated health care system, providing care at 1,250 health care facilities and serving nine million enrolled Veterans each year. The long-term care Veterans receive within this centralized healthcare system provides a rich source of longitudinal patient data, which covers patients through periods of health and illness. This is unique to the VHA, as the care patients receive in other US health care organizations is often fragmented among different clinical sites, making it difficult to obtain a complete patient profile through the aggregation of medical records.
The VHA integrated health care system offers many untapped opportunities to gain insights from patient data to advance cancer research and care. BD-STEP provides an avenue to access the rich, diverse data available in the VA Electronic Health Record (EHR), including longitudinal clinical patient data and diagnosis and treatment information from the VA Central Cancer Registry. BD-STEP utilizes the expertise of early-career data scientists to analyze these data and facilitate the execution of large-scale system changes in clinical care.
Fellows are placed in VA medical centers across the country to work with clinicians and interdisciplinary researchers to address important patient-centered health challenges. The fellowship is centrally managed by a Coordinating Center which hosts a National Curriculum and works closely with sites to monitor fellows’ progress. The Coordinating Center is guided by a steering committee with VA and NCI membership, including the NCI’s Center for Strategic Scientific Initiatives, Center for Cancer Training and Center for Biomedical Informatics and Information Technology.
Over the course of their research, fellows network with health care and data science experts across government, industry and academic institutions. They receive research mentorship from VA health care providers and academic researchers and curriculum oversight by VHA and NCI program leadership. This equips BD-STEP graduates with the skills and connections they need to pursue careers in health care data science after graduation.
Since the launch of the program, BD-STEP fellows have initiated diverse studies using VA health care data resources. These including predicting hepatocellular carcinoma in hepatitis VA patients using a cohort of more than 180,000 Veterans, comparing frailty assessment via clinical teams and machine learning to predict mortality in patients with congestive heart failure, and characterizing dynamic biological changes associated with prostate cancer progression in obese patients.
In addition to each fellow's individual research project, funded fellows spend 25% of their time on a Service Project that is of direct value and impact to the VA health care system and/or the fellowship. Service projects will be selected by the BD-STEP Coordinating Center based on their significance and impact on identified program and health care system needs. Examples of past service projects include: working with the National Artificial Intelligence Institute, supporting operations of the National Precision Oncology Program, and working with the Innovation Ecosystem to examine the social determinants of health related to COVID
Developing and establishing fruitful collaborations with scientific peers is a vital component of a successful research career. BD-STEP provides various opportunities for fellows to form partnerships with researchers and organizations within VA as well as with academic institutions, commercial enterprises and other government agencies. While the fellowship maintains formal collaborations with key VA organizations working within the data science space, as well as with the National Cancer Institute, the fellows’ individual research projects are also typically multi-institutional efforts (listed below).
VA and NCI coordinate biannual in person meetings for the fellows, which are typically co-located with relevant scientific conferences to maximize the educational experience. During these meetings, fellows present updates on their research findings and engage in discussions that are meant to spark collaborative projects and sharing of helpful tools. Invited speakers present relevant topics to support fellows' training and research activities.
Applicants must meet all three criteria:
- POSTDOCTORAL RESEARCHERS
Applicants must have obtained a PhD in engineering, computer science, physical science, or other related discipline including:
- Engineering disciplines
- Computational Biology
- COMPUTATIONAL SCIENTISTS
In addition to a history of collaboration and teamwork with strong communication skills, applicants must have:
- Experience in bioinformatics, modeling, or management of large data sets
- Strong background in advanced mathematics and statistics
- Proficiency in at least on programming language
- US CITIZENSHIP
Applicants must be US citizens to be hired within a VA facility. Non-citizens are also encouraged to apply but are not eligible for VA stipend support.
How to Apply
- Contact your site of interest and discuss research projects.
- Have an academic mentor complete a letter of support for participation in the program.
- Compose a brief statement (no more than one page) describing interest and fit within the program, including proposed research areas and topics.
- Complete application and submit the following materials:
- Letter of support from academic mentor
- Statement of interest
- Curriculum Vitae (CV)
Want to Learn More?