Research Data Analyst 2 (2 Years Fixed Term)

Key Skills

AWS, Azure, Data Analysis, Database, Econometrics, Effective communication skills, Finance, Large data sets, Machine learning techniques, Project management, Python Programming, Statistics

Job Description

The Center for Population Health Sciences (PHS) at Stanford University School of Medicine is seeking a Research Data Analyst 2 (2-year fixed term) for data management, data analysis, and data science work focused on population health and health equity serving the American Family Cohort Consortium. The American Family Cohort (AFC) is a national EHR dataset comprised of over 7 million unique individuals from a variety of sources. These data have been used for research in health economics, health services and health equity. We seek an individual with an interest in population health and primary care, health equity, quality and continuity. The ideal applicant will have experience in AI, ML or NLP in EHR data or a strong interest in applying these methods to primary care.

The Research Data Analyst will specifically work on a project in collaboration between PHS the Centers for Disease Control and Prevention (CDC). The main research includes monitoring COVID-19 hot spots and trends, and to obtain the analytic products and deliverables to inform the COVID-19 emergency public health response and working closely with physician collaborators on quality and continuity metrics in clinical care both before and during the pandemic. Although the project is for a fixed 2 years term, it is likely the position is extended indefinitely as other opportunities arise at PHS and the AFC research cohort expands.

This position will be primarily responsible for managing and analyzing AFC, a large, rich, national EHR dataset. The applicant should be comfortable with data management and cleaning and statistical analyses. The Research Data Analyst is expected to be exposed to working in the cloud environment and learning machine learning techniques. The role requires working independently with minimal supervision, as well as communicating results in code, orally, and in writing to internal and external researchers and stakeholders. This position will also be expected to curate and create new derivative datasets and perform data management procedures, including data security, as well as train and update other researchers and staff on these procedures. In addition, the position requires project management skills helping to move projects along for internal and external collaborators and assisting in the design and management of new projects. This position provides ample opportunity for first author publications.

About Center for Population Health Sciences

We enter the world with a set of genes that determine many factors of our health. From that moment forward, every aspect of our lives affects our health. There is unequivocal evidence that social, environmental, and behavioral factors are by far the strongest predictors of health and disease. Founded in 2015, the Stanford Center for Population Health Sciences' (PHS) mission is to improve population health by bringing together diverse disciplines and data to better understand and address the social and environmental determinants of health. This position will work with PHS’s most valuable datasets to advance the goal of reducing premature morbidity and mortality and disparities in health outcomes.

Duties include:

• Prioritize and extract data from a variety of source including a large, national, granular, high value health dataset held by PHS. These datasets include EHRs, claims, survey data, medical reports, and laboratory data. The position will be expected to perform quality checks and ensure data are accurate and complete.
• Determine additional data collection and reporting requirements.
• Design and customize reports based upon data in the database. Monitor regulatory compliance for utilization of the data.
• Perform data quality checks to identify potentially problematic data, make corrections, and eliminate root cause for data problems or justify solutions to be implemented by others.
• Create complex charts and databases, perform statistical analyses, and develop graphs and tables for publication and presentation.
• Serve as a resource for non-routine inquiries such as requests for statistics or surveys.
• Provide documentation based on audit and reporting criteria to investigators and research staff.