Postdoc Fellow: Causal Inference Methods Using Health Records

Cambridge

Competitive Salary, Bonus & Benefits

Do you have expertise in, and passion for, causal analysis of health records? Would you like to apply your expertise to impact the assessment of treatment effectiveness for AstraZeneca’s life changing medicines? Then this could be the ideal next step in your career.

About AstraZeneca:

AstraZeneca is a global, science-led, patient-centred biopharmaceutical company that focuses on the discovery, development and commercialization of prescription medicines for some of the world’s most serious disease. But we’re more than a leading pharmaceutical company. At AstraZeneca, we’re dedicated to being a Great Place to Work where you are empowered to push the boundaries of science and fuel your entrepreneurial spirit. There’s no better place to make a difference to medicine, patients and society.

About the Postdoc Programme:

Bring your expertise, apply your knowledge, follow the science and make a difference.

AstraZeneca’s Postdoc Programme is for self-motivated individuals looking to tackle exciting, high impact projects in a collaborative, engaging and innovative environment. You’ll work with peers and professionals from a diverse group of backgrounds, and a world class academic mentor specifically aligned to your project. We’ll help you develop valuable networks which support your research and future career development!

AstraZeneca Postdocs are respected as specialists and encouraged to speak up. They lead ground-breaking drug discovery and development research projects. Our vibrant, multi-disciplinary scientific teams empower and support our Postdocs, and we encourage them to share their research at conferences, publish papers, achieve their goals and make a difference to our patients.

You’ll learn from industry leaders working on innovative research across our organization. Our Postdoc Training Programme will support you to develop transferrable skills from influencing others to shape the agenda, to data analysis.

Are you ready to explore this exciting next step in your research career? Apply today!

About the Opportunity:

We want to transform healthcare, change the lives of billions of people for the better and address some of the biggest healthcare challenges facing humankind. Our ambition is to stop the progress of often degenerative, debilitating, and life-threatening conditions, achieve remission, and one day cure them. Our work on real world evidence, generated from electronic health records and health insurance claims data, plays a vital role in supporting our drug development.

While randomised clinical trials are the gold standard for determining drug efficacy, observational (real-world) studies are often needed to better understand their safety and effectiveness once drugs reach the market. Real world studies can also be used to assess drug effectiveness against other diseases, highlighting opportunities for repurposing. However, concerns over the quality of results of real-world studies have been raised due to biases that may arise from the lack of randomisation. Bias can be reduced with widely used analysis methods that mimic the randomisation process (e.g. propensity score matching), and further opportunities to reduce these biases and improve the accuracy of real-world evidence need to be identified.

The main focus of this research is to study whether using controls or novel statistical or machine learning approaches can be used to improve the accuracy of estimates of treatment effectiveness from health records or claim data.

In leading this research you will be embedded within a team of health informaticians and statisticians, where you will perform causal analyses using real world data, supported by academic mentor Prof James Carpenter. You will apply standard methods (propensity score matching) and novel statistical and machine learning approaches, to compare performance in impactful projects and on benchmarks to allow fair systematic comparisons. You will gain broad exposure through training and experience in how data science, innovative statistics and machine learning are used within the pharmaceutical sector. Your work will help to establish best practices used throughout AstraZeneca, and will contribute to the development of life-changing medicines for our patients worldwide.

Qualification, Skills & Experience

Required:

  • A PhD (or equivalent) in a quantitative field
  • Proficient in programming languages for statistical computing, such as R or python
  • Experience with multivariable models, machine learning or matching methods
  • Enthusiasm for exploring new approaches for causal inference from observational data, including machine learning
  • Good networking, collaboration and teamworking skills
  • Highly organised and systematic
  • Ability to see opportunities, learn, and apply that learning to drive innovation

Desirable:

  • Research experience using real world data (e.g. health records or health insurance claims)
  • Experience in Structured Query Language (SQL)
  • Application of propensity score techniques
  • Strong publication record

This is a 3-year programme. 2 years will be a Fixed Term Contract, with a 1-year extension which will be merit based.

Ready for an exciting, rewarding challenge? Apply today!

Advert Opens: 26th October, 2021

Advert Closes: 5th December, 2021

If you require any reasonable adjustments or accommodations during your application or interview process, please let us know.

More Information

Privacy Policy / BBSTEM Limited | Registered in England and Wales | Company No: 11127036