Georgia Tomova

Photo of: Georgia Tomova


Doctoral Student

Cohort year


Partner Institution


Georgia is a health data scientist from the Leeds Institute for Data Analytics whose main interest is using causal inference methods to improve health research, and more specifically the field of nutrition. She graduated from the University of Leeds with a BSc in Nutrition, followed by an MSc in Health Data Analytics, which she considers to be the most eye-opening experience of her academic and professional development. It was during her MSc that she was introduced to Causal Inference methods, and being aware of the many malpractices and pitfalls in nutrition research, she developed a keen interest in this area. The combination of her technical skills and domain knowledge meant the multidisciplinary environment of The Alan Turing Institute was a good match for her, which is what motivated her to become a Turing Doctoral Student.

Research interests

There has been a continuous debate around the validity of causal effect estimands and subsequent findings in nutritional epidemiology, which are complicated by the fact that energy and dietary data are compositional. Georgia’s PhD is focussed primarily on understanding causal effect estimands in nutritional epidemiology. Her research involves using simulations to examine the challenges surrounding modelling strategies for energy intake adjustment and nutrient substitution, by exploring the performance of different methods, and clarifying the corresponding causal effect estimand and interpretation of each. She will then go on to cover more complex challenges, such as developing alternative modelling strategies for energy and dietary adjustment with the use of latent variable methods, and will explore the extent to which the assumptions of consistency and positivity are met in nutritional epidemiology.

Georgia’s interests lie within the field of causal inference, and more specifically in evaluating and improving the methods currently used in epidemiology. She is passionate about improving the quality of applied health research, as well as the teaching and use of contemporary causal inference methods. She is a co-leader of the Causal Inference Special Interest Group at the Institute, and has been part of delivering the Leeds Institute for Data Analytics Summer School in Causal Inference.