Lorentzlezing: Can predicting the future help us to make better decisions about our health?

Can predicting the future help us to make better decisions about our health?

Many apps and websites provide calculators of our individual risk of developing a disease using information about our age, lifestyle, our current health etc. It is expected that advances in artificial intelligence will make such predictions increasingly accurate. But what happens if we make decisions based on these predictions? For example, what if we change our lifestyle or start to use certain medications? Most algorithms don’t give reliable answers to this question. In this lecture we will discuss how we can develop new tools, in particular causal prediction algorithms, that use health data in such a way that we are able to predict what our risk of a disease would be if we made certain decisions.

About the speakers

Daniala Weir is an assistant professor of real world evidence working in the Division of Pharmaco-epidemiology and Clinical Pharmacology at Utrecht University. She obtained her PhD in Epidemiology from McGill University and completed a Post-Doctoral Fellowship at the University of Toronto (Canada). Her work centers around improving the safety and effectiveness of medications for individuals living with multimorbidity using real-world data, with particular focus on patients with diabetes.

Nan van Geloven is an assistant professor working at the Department of Biomedical Data Sciences at the Leiden University Medical Center. Her work focusses on causal prediction of time-to-event outcomes using both observationally collected health data and data collected in randomized controlled trials. She has developed and applied statistical methods in multiple disease areas including reproductive medicine, neurology, kidney and liver transplantation.

Ruth Keogh is a professor of Biostatistics and Epidemiology working at the Medical Statistics Department of the London School of Hygiene and Tropical Medicine. The aim of her research is to apply and develop statistical methods for answering questions about the effects of treatments on health outcomes using ‘observational’ data collected about patients in the course of their usual care. She focusses on multiple disease areas including cystic fibrosis, organ transplantation, and Covid-19.

This public lecture is part of the workshop Counterfactual prediction for personalized healthcare.

Practical information
This lecture will be held in English.
Where: in the lecture hall of the museum
When: on Tuesday the 6th of December from 17.30 to 18.30 hrs. 
Costs: you can attend this lecture with a museum ticket
Registration: please use the form to register for this lecture