Data Scientist / Health Science Specialist

Data Scientist / Health Science Specialist The role is based within a leading healthcare system in New England that serves as a major referral center and a hub for clinical research. The organization is seeking a Data Scientist/Manager to support research aimed at improving cancer care for older, frail, and multimorbid patients who are often underrepresented in clinical trials. The position offers the opportunity to lead data-driven projects that inform clinical decision-making and enhance outcomes for diverse patient populations. Under the supervision of Principal Investigators and senior scientific staff, the Data Scientist/Manager will lead data management, analysis, and annotation across multiple projects evaluating the real-world benefits and harms of cancer treatments. The program integrates clinical outcomes, health services, and qualitative data to generate evidence that informs both retrospective analyses and prospective implementation. This work supports a learning healthcare system in which insights from existing data directly guide the development, testing, and refinement of clinical decision support and care delivery strategies for older Veterans with cancer. You will join a multidisciplinary team of clinicians, statisticians, and data scientists at a nationally recognized, Age Friendly academic VA health system affiliated with Harvard Medical School and Boston University School of Medicine. This role offers a unique opportunity to apply data science skills to high-impact research that translates real-world evidence into improved, patient-centered cancer care for older patients.

PRIMARY DUTIES

Perform annotation, coding, and documentation of clinical, qualitative, and unstructured text data according to study protocols, under the supervision of the PIs, Co-Is, and other advisors. Assist with preparation, cleaning, management, and organization of datasets for all study aims, including merging data sources, recoding variables, and deriving new variables as needed to produce analysis-ready datasets. Lead and support statistical and machine learning analyses for all project aims (e.g., descriptive analyses, regression models, longitudinal analyses, predictive modeling, and NLP-based information extraction), under the direction of the study investigators. Use advanced data analysis methods from machine learning, artificial intelligence, and applied statistics to build and refine predictive models of healthcare outcomes from large-scale VA EHR data. Assist with implementation and documentation of efficient, reproducible workflows for data management, analysis, and reporting, including version‑controlled code and standard operating procedures. Contribute to the development, implementation, and maintenance of secure procedures for data collection, transfer, storage, and access, in compliance with information security and privacy policies. Conduct data quality checks (e.g., range checks, logic checks, missing data review) and coordinate resolution of data discrepancies with research staff and collaborating sites. Generate standard and ad hoc data reports, tables, visualizations, and data extracts for investigators, project staff, sponsors, and regulatory bodies as needed. Maintain up-to-date data dictionaries, codebooks, and process documentation to support transparency, reproducibility, and effective onboarding of new team members. Participate in project coordination activities, including scheduling and attending team meetings, documenting data‑related decisions, and tracking progress on data tasks. Assist with administrative and regulatory tasks related to data and research operations, including but not limited to preparation, submission, and maintenance of IRB materials, R&D Committee documents, data use agreements, and other regulatory compliance documentation. Collaborate effectively with multidisciplinary team members (e.g., clinicians, statisticians, qualitative researchers, coordinators, programmers, and informaticians) to ensure that data and analytic needs are clearly defined and met. Support preparation of data‑ and methods‑focused sections of manuscripts, abstracts, presentations, and grant applications as requested.

MINIMUM QUALIFICATIONS

MUST be a US Citizen and MUST clear a US government background check. Resumes must clearly identify employment dates, whether each position was full‑time or part‑time, and the number of hours worked per week for all positions listed in the work experience section. Occupational Requirement for Health Science Specialist (601 Series): Bachelor’s or graduate/higher level degree: mandatory study in an academic field related to the medical field, health sciences, or allied sciences appropriate to the work of the position. This degree must be from an educational program from an accrediting body recognized by the U.S. Department of Education at the time the degree was obtained. Candidate must have had professional work in grants administration; qualifying experience is considered to be experience in grants administration in areas of science, medical, and healthcare fields similar or related to the work of the position. Such experience must have involved professional judgment of a kind and level of difficulty and responsibility essential to successful performance in the position to be filled. Qualification Standards for Data Scientist (1560 Series): Mathematics, statistics, computer science, data science, or a field directly related to the position. The degree must be in a major field of study (at least at the baccalaureate level) that is appropriate for the position.

– OR –

Combination of education and experience: Courses equivalent to a major field of study (30 semester hours) as shown above, plus additional education or appropriate experience.

PREFERRED QUALIFICATIONS

Demonstrated experience with data management and analysis in a research, healthcare, or similar setting (e.g., cleaning data, managing large datasets, performing statistical analyses, developing predictive models). Proficiency in at least one major programming language used for data science (e.g., Python, R), and experience working with relational databases (e.g., SQL). Experience working with clinical, EHR, or claims data, particularly in oncology, geriatrics, multimorbidity, or related areas. Strong written and verbal communication skills, including the ability to explain complex analytic concepts to non‑technical audiences and collaborate effectively with multidisciplinary teams. Familiarity with reproducible research practices (e.g., version control, scripted workflows) and principles of data security, privacy, and regulatory compliance in human subjects’ research. Prior experience in a VA, academic medical center, or similar healthcare research environment is highly desirable. #J-18808-Ljbffr VA Boston Healthcare System