Mission: Structure and define data set deliverables (which we call data specifications or data specs for short) to address our clients’ complex clinical objectives. Decide how to build, validate and interpret the resulting data sets. You feel passionate about improving people’s lives through rigorous data analysis. This is a complex role ideal for someone who wants to begin a career as a clinical data scientist.
This role will be based in Houston, TX, but should expect to travel to visit clients on site (within the United States) 3 to 10 times a year.
- Assess whether data specs have basic clinical validity in 3 months
- Assess whether data specs are adequate for data engineers and quality assurance in 3 months
- Document client needs on clinical topics, with help from senior data scientists, in 3 months
- Understand the basic data structures and data limitations of medical claims data sets, including diagnosis and medical procedure data coding systems, in 3 months
- Articulate medical claims data flows in 3 months
- Read and correctly interpret simple SQL queries written by others in 9 months
- Generate new data specification from scratch by listening to customer requirements in 6 months
- Internally, “speak for clients” and defend how data specs address their needs in 6 months
- Articulate major data flows (medical claims, pharmacy claims, electronic prescribing, and lab results) within the U.S. healthcare industry in 9 months
- Document client needs on clinical topics by yourself in 9 months
- Perform simple data analysis in support of the investigation of client topics in 12 months
- Write simple SQL code to create the data sets you design in 24 months
Competencies: Experience with one or two of the following three: technical writing, data science or working in the healthcare industry. We will teach you the rest.
- Write and communicate clearly
- Typing speed 55 Words Per Minute
- Willing to laugh at bad jokes sometimes
- Experience with technical writing, interviewing or reporting on complex topics, or preparing written materials to communicate a complex topic
- Healthcare industry experience, with a focus on understanding clinical workflows. You know how the diagnostic process occurs and how patient experiences with the healthcare system change as a result. You understand terms like tertiary care, primary care and emergent care
- Data science experience. Specifically, articulating the limitations and advantages of various data structures, encoding schemes and data normalization efforts
- Data engineering basics. Understand the process for cleaning messy data and transforming it from raw incoming formats to more useful formats
- Medical Billing or Medical Claims data analysis
- Programming ability: especially R, SAS or Python for data analysis (pandas, Jupyter, etc)
About CareSet Systems
Careset Systems (https://careset.com) decodes Medicare claims data to guide new drug launches for pharmaceutical companies. Using the largest single cohort of patients available, CareSet groups Medicare claims into patient journeys by disease, then tracks how their diseases progress and which teams of doctors treat them. With CareSet, promising drugs find the right patients faster, and at a lower cost.