NLM Health Scientist

Lexical Intelligence, LLC•Bethesda, MD

56d•$55,000 - $75,000

About The Position

NLM Health Scientist Lexical Intelligence provides software and services related to processing large-scale biomedical information sources. Our Natural Language Processing (NLP) and analytics software is used by policy and decision makers to evaluate and prioritize current and emerging areas of research. We are looking for a Health Scientist to work within the Lister Hill National Center for Biomedical Communications (LHNCBC). The Health Scientist will have experience in clinical data curation, biomedical data analysis, and health informatics. The Health Scientist will have a firm understanding of healthcare coding systems, data standards, and controlled clinical terminologies. The Health Scientist shall be able to work well within a team of clinicians, epidemiologists, biostatisticians, researchers, data engineers, and subject-matter experts. The selected applicant will be subject to a pre-employment background and reference check. Start dates will be dependent on successful completion of an NIH background check through the Division of Personnel Security and Access Control (DPSAC).

Requirements

Bachelor's or advanced degree in Health Informatics, Biostatistics, Epidemiology, Public Health, Data Science, or related fields
Proficiency in one or more statistical programming languages (e.g., Python, R, SAS) and database programming languages (e.g., SQL)
Strong experience transforming complex raw data into analysis-ready datasets tailored to specific research questions or researcher needs
Strong foundation in statistics or biostatistics, including study design, exploratory analyses, statistical modeling, and interpretation of results
Experience preparing user documentation and educational materials that enable researchers to use complex datasets appropriately
Experience developing and preparing results for reports, presentations, publications, or other products for both technical and non-technical audiences
Strong written and verbal communication skills, with the ability to explain complex clinical, statistical, and data management concepts clearly to diverse audiences
Strong interpersonal and project management skills, with the ability to prioritize and manage multiple work streams with competing deadlines
All candidates will be required to undergo a background check
Must be authorized to work in the United States.

Nice To Haves

Demonstrated experience working independently with clinical data, including electronic health record (EHR) data, claims data (preferably CMS Medicare or Medicaid), registry data, or public health data sources
Prior experience and demonstrated ability to understand healthcare coding systems, data standards, and controlled clinical terminologies, including ICD-10-CM, SNOMED CT, CPT/HCPCS, LOINC, and RxNorm
Experience performing statistical analyses using clinical, biomedical, claims, survey, and laboratory datasets, including complex survey data
Ability to apply appropriate methods for cohort definition, patient identification, variable derivation, outcome construction, and analysis of healthcare utilization and clinical outcomes
Experience providing methodological and analytic consultations to researchers regarding dataset selection, research feasibility, analytic methods, and interpretation of findings
Ability to conceptualize and support research studies from initial question development through study design, analytic-plan development, data analysis, interpretation, and dissemination of findings
Experience collaborating with multidisciplinary teams including clinicians, epidemiologists, biostatisticians, and data engineers while maintaining clear ownership of assigned deliverables

Responsibilities

Curate datasets from complex clinical data sources, including electronic health records, health information systems, administrative claims data, population health surveys, public health data, and laboratory information systems
Develop custom analytic datasets by cleaning, transforming, harmonizing, and validating data
Evaluate data for completeness, accuracy, consistency, representativeness, and suitability for specific research use cases by assessing dataset structures, variables, coding conventions, file types, and technical documentation
Develop reproducible data processing and quality control processes, including procedures for identifying missing values, duplicate records, outliers, coding discrepancies, and inconsistencies
Describe clinical datasets for secondary use, including their provenance, represented populations, collection methods, variable definitions, limitations, linkage considerations, and appropriate analytic applications
Develop clear public-facing resources including user guides, data dictionaries, technical documentation, presentations, and training materials to help researchers understand and appropriately analyze clinical datasets
Identify opportunities to improve dataset utility, documentation, and the overall research value of curated data assets
Protect sensitive health information and adhere to all applicable privacy and security requirements
Ensuring compliance with organizational security and privacy policies, protecting sensitive data and systems, reporting security incidents, and participating in required cybersecurity training.
Implementing best practices related to access control, data handling, and risk mitigation within the scope of assigned duties.