Markov Models for Fun and Profit

Johanna Brinne Roos

Data Scientist

Center for Innovation in Karolinska University Hospital, Stockholm


Johanna works as a data scientist at the center for innovation in Karolinska University Hospital Stockholm. She holds a PhD in theoretical physics, but has since her since her dissertation in 2009 worked with health economic modeling and predictive modeling. She started working at the center for innovation in 2015 where she uses large volumes of patient level data to investigate the benefits of new care methods.

Session Outline

A health economic evaluation is the comparative analysis of alternative courses of action in terms of both their costs and consequences in order to assist policy decisions. To be able to compare two different care methods a care flow Markov model for Karolinska has been created.

When the model is populated with large volumes of patient level data for a patient group from the hospital the care flow algorithm as decision support enables identification of patients in that group benefiting from a new care method. If implemented It can help decision makers to make smarter decisions, guide hospital care in the right direction and make care profitable for the entire patient group and health care provider.