Staff Data Scientist

Abbott is a global healthcare leader that helps people live more fully at all stages of life. Our portfolio of life-changing technologies spans the spectrum of healthcare, with leading businesses and products in diagnostics, medical devices, nutritionals and branded generic medicines. Our 114,000 colleagues serve people in more than 160 countries.

     

JOB DESCRIPTION:

Working at Abbott

At Abbott, you can do work that matters, grow, and learn, care for yourself and family, be your true self and live a full life. You’ll also have access to:

·         Career development with an international company where you can grow the career you dream of.

·         Free medical coverage for employees* via the Health Investment Plan (HIP) PPO

·         An excellent retirement savings plan with high employer contribution

·         Tuition reimbursement, the Freedom 2 Save student debt program and FreeU education benefit - an affordable and convenient path to getting a bachelor’s degree.

·         A company recognized as a great place to work in dozens of countries around the world and named one of the most admired companies in the world by Fortune.

·         A company that is recognized as one of the best big companies to work for as well as a best place to work for diversity, working mothers, female executives, and scientists.

The Opportunity

 Staff Data Scientist works as integral part of a collaborative data and analytics team and responsible for analyzing real-world data to generate insights and develop machine learning models that drive the development and optimization of devices in Abbott Diabetes Care.  The role requires drawing insights, and presenting results in a cohesive, intuitive, and simple manner to the functional stakeholders utilizing technologies to collect, clean, analyze, predict, and effectively communicate insights. Key functional stakeholders include research & development, clinical, medical, regulatory and market access teams.

What You'll Work On

• Analyze large real-world datasets including device data, electronic health records (EHR), claims data, labs, and patient registries.
• Support the design and execution of RWE studies including but not limited to:
  • Treatment optimization and understanding treatment patterns
  • Comparative effectiveness analyses
  • Drug and device utilization
  • Natural history and burden of disease
  • Healthcare resource utilization
• Analyze data, draw insights, and present results in a cohesive, intuitive, and simple manner to functional stakeholder.
• Utilize technologies to collect, clean, analyze, predict, and effectively communicate insights such as model logic and restrictions.
• Conduct advanced statistical analysis to determine trends and significant data relationships.
• Develop machine learning models to apply test data algorithms to future data.
• Validate models/analytical techniques and develop algorithms to execute analytical functions.
• Collaborate with clinical, medical, regulatory, and market access teams to integrate RWE into product development and lifecycle management.
• Work closely with the functional stakeholders to understand the domain and iteratively refine analyses.
• Provide learning and educational pathways for team members.
• Provides input into developing departmental and site processes and procedures.
• Guide and otherwise contribute to technical teams in development, deployment and application of applied analytics, predictive analytics, prescriptive analytics, etc.
• Independently manages and consults in multiple complex projects working with stakeholders to define business questions, requirements, timelines, objectives, and success criteria to address needs.
• Experience in creating and advanced statistics such as: regression, time-series forecasting, clustering, decision trees, exploratory data analysis methodology, simulation, scenario analysis, modeling, optimization, unstructured data analysis, and neural networks.
• Researches and adapts existing open-source algorithms when possible and develops novel techniq