Classification: Contract
Contract Length: 12-months

Position Summary

The Senior Research Scientist is an important member of the Health Sciences & Population Health Research (HSPHR) team at HCA. The Senior Research Scientist will focus on incorporating our data resources into research operations, participating in and leading scientific teams that will help HSPHR maximize the potential of available data, and conduct collaborative multicenter research studies and trials. Specifically, this position will provide statistical consultation, analysis of data, interpretation of results and preparation of reports related to the multicenter rollout of INSPIRE prompts and preliminary assessment of a related prospective randomized controlled trial. A requirement of this position is a comprehensive understanding of healthcare-based research specializing in health services, quality improvement, implementation science, and health policy as well as in-depth knowledge of the components of the INSPIRE 1 and INSPIRE 2 trial protocols and results.

Responsibilities

• Use data wrangling skills and learn techniques specific to HCA data systems.
• Provide statistical input and support related to study design and in the development of protocols
• Advise on database design and documentation to ensure that all data required for analysis purposes are captured adequately
• Develop randomization schema
• Develop statistical analysis plans (SAP)
• Perform hypothesis generation and testing, in particular data-oriented discovery methodologies such as cross validation. These functions are performed in a mathematical environment such as R or SAS.
• Oversee and manage SQL server.
• Experience extracting data from HCA’s EDW
• Troubleshoot missing collection of information from HCA facilities
• Model, analyze and visualize structured and unstructured data using advanced analytical techniques and tools
• Write statistical portion of manuscript based on results of analysis and address manuscript revisions based on reviewer's comments.
• Deliver predictive and prescriptive solutions leveraging machine learning (ML) and artificial intelligence (AI), as needed
• Perform analytics using regression and classification techniques such as logistic regression, boosting, SVM and neural networks
• Clearly communicate the nature and results of complex analytics to non-technical users in written, spoken and visual means.
• Work to broaden and hone their analytics and statistics skills to develop expertise in working with HCA clinical, operational and financial data.
• Investigate defined problems, gather data and input, and seek guidance for determining root causes.
• Understand and check for bias, inaccuracy and omission, including through the consultation of other experts and the integration of multiple data sources.
• Build relationships within the service lines and across multi-disciplinary teams to assist in facilitating discussions regarding data outputs and feedback on usage activities to improve research output.
• Hold discussions and prepare documents for colleagues.
• Seek and share opinions, and input. This includes asking questions well, seeking feedback and appropriately handling conflict.
• Work with both clinical and business customers to define questions, explore solutions and present results with an expectation of constant contact, communication and iteration.
• Use multiple sources for technical, analytical and professional development.
• Continue to build skills in critical thinking, research methodology, and healthcare industry data.

Requirements

• 5+ years of experience working in research and scientific publications and programming
• Experience with managing big data
• Minimum of a Master’s degree in Data Science or related field.
• Analytical and technical skills with ability to interpret issues, assess technical risks, and recommend solutions in a timely manner.
• Understanding of the relational model as it pertains to SQL development.
• Basic understanding of and experience with BI tools, NoSQL databases, model fitting processes (cross validation), analytic environments (Teradata, R, SAS, SPSS), statistical techniques (regression and hypothesis testing) and Big Data environments (Hadoop and its ecosystem).
• Exposure to machine learning techniques, such as boosting, SVMs and neural networks.
• Adeptness to learn new assignments, technologies, and applications quickly and manage multiple assignments simultaneously.
• Proven ability to form stable working relationships internally. Contacts are primarily with direct supervisor and other professionals within the work group or department.
• Demonstrated skills to work independently and follow standard practices and procedures.
• Strong communication and interpersonal skills to work in a high profile and fast-paced team.
• Technical aptitude to learn and adapt to new industry applications and tools.