Associate Professer Ruth Keogh, Department of Statistics, London School of Hygiene and Tropical Medicine
MRC INTEGRATIVE EPIDEMIOLOGY UNIT (IEU)
Thursday, 16th February, 2017
16.00 – 17.00 - Room OS6 – Oakfield House
Associate Professor Ruth Keogh
Department of Medical Statistics
London School of Hygiene and Tropical Medicine
Dynamic prediction of survival using landmarking in large healthcare databases,
with an application in cystic fibrosis
In ‘dynamic’ prediction of survival we make updated predictions of individuals’ survival over time as new information becomes available about their health status. Landmarking is an attractive and flexible method for dynamic prediction.
Large observational patient databases provide longitudinal data on clinical measurements and present opportunities to develop ‘personalised’ dynamic predictions of survival. This work is motivated by the aim of developing dynamic prediction models for survival in people with cystic fibrosis, one of the most common inherited life-shortening diseases, using the US Cystic Fibrosis Patient Registry, which contains longitudinal clinical data on over 40,000 people. I will discuss some of the challenges faced in making dynamic predictions of survival in this data and show how they can be addressed in the landmarking framework. I will also show some comparisons between landmarking and the alternative approach of joint modelling of longitudinal and survival data and hopefully convince you that landmarking has a number of advantages.
Ruth Keogh is an Associate Professor in the Department of Medical Statistics at LSHTM, where she has been based for over 4 years. Ruth studied Maths at the University of Edinburgh before getting her MSc in Applied Statistics and DPhil in Statistics at the University of Oxford. Ruth is currently funded by a MRC Methodology Fellowship and is focusing on methods for dynamic prediction of survival in complex observational data using landmarking, and extensions of landmarking to address other questions in survival analysis. She is especially interested in applications in cystic fibrosis. Ruth’s other research interests include case-control study design and analysis, methods for handling missing data and measurement error and causal inference methodology.