Computercraft is seeking a Biomedical Data Analyst to support the National Library of Medicine (NLM) at the National Institutes of Health in Bethesda, Maryland. NLM is the world’s largest biomedical and health research library and maintains a preeminent collection of biomedical literature and information resources. To make biomedical and life sciences literature accessible, NLM maintains PubMed (a publicly accessible search engine), which includes MEDLINE, a bibliographic database with more than 31 million references. MeSH (Medical Subject Headings), a distinctive feature of MEDLINE, is NLM’s controlled vocabulary thesaurus that gives uniformity and consistency to the references.
In this role, you will work full-time providing data analysis and computational support for data-driven efforts to evaluate and improve the MEDLINE indexing product. Working under the technical direction and oversight of the Senior Biomedical Data Analyst and within established analytical approaches, you will support the processing, preparation, validation, and analysis of datasets, including PubMed web search and API user log data, used to evaluate MeSH vocabulary and automated MeSH indexing algorithm performance. You will assist with analyses of indexing performance and user search behavior and contribute to the development of data products, reports, and other analytical outputs used to inform improvements to MEDLINE indexing.
Work performed by the Biomedical Data Analyst is subject to technical review and quality assurance by the Senior Biomedical Data Analyst. The Biomedical Data Analyst shall incorporate feedback, make necessary corrections, and maintain analytical code, documentation, and work products in accordance with established methodologies, technical standards, and quality requirements.
This is a remote position.
Job Responsibilities Support quantitative analyses evaluating automatic MeSH indexing and its impact on MEDLINE and PubMed users.
Prepare and process PubMed GUI, API, user search and click, bibliographic, indexing, and other relevant datasets for analysis.
Develop and execute scripts for data extraction, cleaning, transformation, aggregation, validation, and analysis using established analytical methods and requirements.
Assist with the development, execution, testing, and maintenance of reproducible data processing and analytical workflows.
Perform exploratory data analysis and apply established statistical and quantitative methods to identify patterns, trends, anomalies, and relationships in data.
Calculate and report established performance measures used to evaluate automated MeSH indexing, vocabulary performance, and related MEDLINE processes.
Conduct data quality checks and investigate missing, inconsistent, anomalous, or unexpected data and analytical results.
Assist the Senior Biomedical Data Analyst with analyses of PubMed user behavior and other data used to identify potential opportunities for improvements to automated indexing algorithms, MeSH vocabulary, or related processes.
Develop tables, charts, summaries, and other analytical outputs to communicate findings.
Document code, data processing steps, analytical procedures, data quality issues, results, and other information necessary to support reproducibility and technical review.
Submit analyses, code, calculations, documentation, visualizations, and other work products for review and quality assurance by the Senior Biomedical Data Analyst.
Address findings identified during technical review and quality assurance, including correcting code, data processing procedures, calculations, documentation, or analytical outputs as necessary.
Follow established analytical methodologies, coding practices, documentation requirements, and quality control procedures.
Participate in the review and interpretation of analytical findings and assist in preparing results for technical and program stakeholders.
Required Skills/Experience B.S.-level or higher education in data science,…