Universiteit Leiden

nl en

Lezing

Florence Nightingale Colloquium presents Francesca Ieva

Datum
vrijdag 28 mei 2021
Tijd
Toelichting
The seminar is targeted at a broad audience, in particular we invite master students, PhD candidates and supervisors interested or involved in the Data Science Research programme as well as colleagues from LIACS and MI to attend. The seminar is organized by the DSO, MI and LIACS.
Serie
Florence Nightingale Colloquium
Locatie
Kaltura Live Room
Francesca Ieva is Associate Professor of Statistics at the Politecnico di Milano in Milan, Italy.

How to manage complexity in Healthcare: new methods and challenges for Health Analytics

The term “Healthcare Data" refer to a huge and widely heterogeneous amount of data arising from current practice in any clinical area. In the last decade, such data was supposed to change the way clinicians, researchers and people in charge with healthcare government carry out their work and think about their mission. Nevertheless, despite the availability of wide sources of data and the great potential for healthcare analytics they provide, it is not always the case that methodological approaches are adequate. In this talk, we will discuss some examples of complex data arising from clinical practice, together with advanced analytics approaches developed in order to properly deal with complexity of such data, and then to extract meaningful information enriching personalized prognostic models. The first scenario concerns the joint use of Functional Data Analysis within a time-to-event framework as a tool for risk stratification and personalized prediction, motivated by a real problem where the overall survival of patients affected by chronic conditions is considered, together with repeated events of hospitalizations and drug purchases, in a pharmacoepidemiological setting. The second one concerns the use of Machine Learning based techniques for predicting the development of toxicity adverse events due to radiotherapy in prostate cancer patients, starting from genomic information.

Join the webinar via Kaltura Live Room

Kaltura Live Room works best in Edge, Chrome and Firefox. Make sure you activate your camera and microphone beforehand in order to interact with the speaker and participate in discussion. The room opens for the public at 12:50.

Register for the Kaltura Live Room link
Deze website maakt gebruik van cookies.  Meer informatie.