Biostatistician Data Scientist Informaticist - PriceSenz
Bethesda, MD
About the Job
Location : IC: NIMHD Street: 6707 Democracy Blvd Bldg.: 2DEM Room: 800 City: Bethesda State & Zip: MD 20892
Weekly Hours - FT: 30-40 hours per week Total No. of Hours : 40
Overall Position Summary and Objectives
- Address big data and data science policies, practices and analytic methodologies.
- Identify big data sources; conduct analyses of secondary data.
- Develop conceptual ideas (data systems, analytic publications) surrounding data science projects, such as the development of the artificial intelligence for minority health and health disparities.
- Contribute to interpretation of big data and identification of data patterns using big data tools, such as Hadoop, Apache Spark, Apache Storm, Cassandra and RapidMiner.
- Identify potential issues in data lakes, algorithms, artificial intelligence/machine learning training, and repositories.
- Use statistical methods for analysing complex data.
Min Education - Master's
Resume Max Pages - 3
Certifications & Licenses
- AI
- Knowledge of Big Data Systems for Health.
- Ph.D. in Statistics with 10+years of experience
Skills (Ranked by Priority)
- Clinical and/or translational research
- Work with large data sets
- Clinical Data Analysis
- Data Quality Control
- Data Harmonization
- Machine Learning
- Data Transfer
- Knowledge of minority health and health disparities and/or general health.
- Strong communications skills, both oral and written.
1, 2, 3, 4, 5 represents priority rankings, where 1 is highest priority and 5 is lowest priority of those ranked
Software
- Hadoop
- Rapid Miner
- Cassandra
- Apache Storm
- Apache Spark
- Outlook
- STATA
- Excel
- SPSS
- SAS
- AI Bias Mitigation Tool
- Word
Field of Study
- Biology
- Community and Public Health
- Miscellaneous Social Sciences
- General Social Sciences
Statement of Work Details
Provides programming and troubleshooting support to the Federal Government in the dissemination of research data.
- Generate and optimize programs and scripts for the analysis of data; create programs and algorithms and develop computational infrastructure resources for organizing and parsing data from large and complex data
- Serve as bioinformatics expert and coordinate with teams of biologists to conduct experimental queries and or perform portions of studies using complex procedures and techniques common to modern bioinformatics
- Coordinate building bioinformatics infrastructure to ensure easy and meaningful scientific analysis and interpretation of data
- Provide broad-based programming and analytic support for a wide variety of bioinformatic and research projects
- Install, troubleshoot and run open-source and commercial scientific software on platforms
- NIMHD provided a leadership role to secure NIH OD funding for and to develop a tool that provides the semantics of common data elements, which is a required basis for the successful adoption and expanded use of CDEs OMOP, FHIR and ULMS exists for clinical and clinical research purposes No such source exists for biomedical research SemNet provides an initial platform and will be the source for further development This resource will be housed on the NIH CDE Repository and enable the expansion and widespread adoption of CDEs for research
Performs computations on research data analysis.
- Perform computational analysis of, and interpret results
- Provide reports based on analysis of scientific data
- Perform sequencing and alignment of raw data, and interpret new data using larger public access datasets
- Provide interpretive analyses of data derived from different experimental platforms to generate biological meaning
- Write custom programs and algorithms to support data analyses and discovery
- NIMHD was successful in securing ODSS Strides funding to secure a cloud computing space to address the looming issue of artificial intelligence machine learning algorithm bias the cloud will host federated data sets for investigators of diverse backgrounds to use for research and for the development of resources, tools and methodologies to mitigate AIML biases and to build community trust in cloud computing
Works with staff on scientific programming and experimental design.
- Collaborate with scientists to design, analyse, manage and interpret all types of data
- Design and execute computational experiments
- Work with staff on planning of experiments, and data analysis for internal and collaborative projects; use bioinformatics expertise to advise and help bench scientists on experimental design and trouble-shooting
- Work with staff to develop specifications for new analysis; design, test and implement solutions
- Make recommendations to investigators about the correct computational tools for testing scientific hypotheses and reaching valid conclusions
Records observations and report results at weekly laboratory meetings.
- Attend scientific and programming meetings; take and compile comprehensive notes; organize and edit content of meeting reports
- Prepare scientific reports and progress reports; assemble data to prepare tables, graphs and slides; conduct scientific and program related information searches and report results
- Maintain proper and detailed documentation of the analysis performed and report results at extramural staff meetings
Provides statistical support / analysis on research data.
- Devise novel methods of statistical analysis for collected data
- Utilize and adapt existing bioinformatics techniques to check for trends and patterns in the data
- Write complex queries to multiple databases
- Perform data processing and data analysis with existing computational and statistical methods
- Assist in evaluating and interpreting results for validity and scientific meaning
- NIMHD is represented on trans-NIH working groups that address all aspects of data science These groups, include
- CDE Task Force, CDE Coordination Touchpoint, Biomedical Information Science and Technology Initiative, Trans-NIH
- Biomedical Informatics Coordinating Committee, N3C Domains addressing SDOH, DATA Sharing and Reuse, ODSS
- Working Group on AI, Ethics, and Transparency for People and Machines, Biomedical Informatics Coordinating Committee, and WHCC Data Harmonization
- NIMHD actively participates in trans-NIH AIML initiatives to increase diversity and to address underrepresented populations in data science fields, including Bridg2AI; AIM-AHEAD; SCH ODSS Cloud Computing in MSIs; and ODSS AI, Ethics, and Transparency for People and Machines
- NIMHD secured 10 Coursera slots for staff training in data science, common data elements, artificial intelligence machine learning and data analytics
Provides research / service goals in the context of the laboratory's overall mission.
- Create novel programs and algorithms that facilitate discovery of knowledge in investigating large and complex data
- Develop and optimize programs and scripts that facilitate organization, integration and data-mining of large data sets; integrate these models into a framework of best practices
- Participate in the design of new protocols involving computational methods
- Work with staff on the development and maintenance of bioinformatics tools, scripts and pipe-lines for data
- Participate in research design with investigators for determining best practices pertaining to the bioinformatics analysis in new and ongoing projects
- NIMHD has conducted several presentations across the US and International to raise awareness of marginalized populations and health disparities concerns in the fields of data science Presentations were made to staff and grantees to raise awareness of data science efforts across NIH and adoption of RAS Titles include: Data Science and Harmonization;
- Big Data for or Against Health Disparities; Bringing the Cloud and Ground Together Using Data Science to Serve
- Communities in Mitigating Health Disparities; and Intersection of Data Technology with Humanity: Plight of Health Disparities
- NIMHD has made a commitment to the Government-University-Industry Research Roundtable GUIRR and the
- National Academy of Sciences; and to the National Academy of Medicine-AHRQ-NIMHD collaboration Race-Based Clinical Algorithms Project Both will foster diverse representation and address relevant issues to mitigate biases that may foster health disparities
Evaluates new types of experimental approaches to protocols based on knowledge of scientific literature, available facilities and research needs.
- Research and review literature to retrieve targeted clinical or scientific information, including novel statistical methods, from publicly available resources
- Collaborate with staff to review current and historical procedures for the acquisition, quality control and management of data
- Analyse and evaluate data cleaning and harmonization needs in the using a variety of descriptive statistics and analytic methods
- Identify new tools and resources for reaching biologically meaningful conclusions
- Collaborate with experimentalists and computational biologists to develop new computational tools to answer research questions of interest
- NIMHD has played a leadership role in the development of Project 5 covid common data elements, which became the foundation for all covid project CDEs
- NIMHD is represented on the NIH CDE Governance Committee, which is charged with endorsing CDEs for NIH that will be hosted in the NIH Common Data Elements Repository at NLM
- NIMHD provided a leadership role to secure NIH OD funding for and to develop a communication plan to foster the adoption of CDEs socialization of CDEs by R01 and other grant mechanism investigators
Independently coordinates the training of personnel in the use of scientific software applications, statistical software applications and programmatic software applications.
- Provide training in and technical support including product updates and version control for programs, algorithms, archives, and pipelines generated during the course of this work
- Instruct staff in computational analysis of data
- Provide ad hoc trainings and hands-on workshops on the use of bioinformatics tools
- Provide training of students, new investigators, and other laboratory personnel in the use of techniques, procedures and equipment to complete the objectives of the laboratory
- Onboard and train staff involved in new clinical trials, including the import of a wide variety of legacy data set; provide rigorous quality control of these data
- NIMHD was successful in securing ODSS Fellow and ODSS Data Scholar to foster interdisciplinary careers that includes health disparity research
Initiates interdisciplinary collaborations with other research centres.
- Work with an interdisciplinary team to apply computational data analysis approaches to make biological discoveries
- Collaborate with group members in experiments associated with data collection
- Interact with all levels of staff and communicate with outside collaborators in the US and abroad
- Work with staff, collaborate with outside researchers, and contribute to positive overall teamwork; teach Bioinformatics principles and methodologies
- Collaborate with biologists, statisticians and/or other bioinformaticians in the design of models summarizing explaining experimental data
- NIMHD is represented on HHS data and data science workgroups, including the Interdepartmental Health Equity
- Collaborative for Data; and the Networking and Information Technology Research and Development Intelligent Robotics and Autonomous Systems 5
- NIMHD assisted in the development of the NIH internal communication plan to socialize CDE
Deliver at least one presentation per year to audiences outside the Government.
- Attend group meetings; present findings; author publications resulting from projects 1
- Present analysis results at research conferences and meetings 3
- Present new research data in group settings, at meetings or seminars 4
- Present scientific and technical data at scientific conferences