At the end of this course, the student
- has insight in the key characteristics and different types of prognostic research
- is able to distinguish the different steps of performing prognostic research
- has insight in different types of missing values
- knows different ways to handle missing values in prognostic research
- has insight in different modelling approaches for prognostic research, including non-linear models
- is able to make a prognostic model
- knows how to derive a prognostic score
- knows how to choose adequate score cut-offs
- knows how to apply modelling techniques to deal with overfitting in small datasets
|
|
| Education form |
Startdate |
Enddate |
Registration period |
| Face-2-Face |
21-3-2022 |
25-3-2022 |
BMS_P3_A |
| Online * |
14-2-2022 |
4-3-2022 |
BMS_P3_B |
*Online courses are only available for Epidemiology students following a full online programme.
Contact details: Educational Office Epidemiology
E-mail: msc-epidemiology@umcutrecht.nl
Registration:
Register via https://www.msc-epidemiology.nl/single-courses.html
Course coordinator:
Ewoud Schuit
Course description:
Prognosis is a key concept in patient care. The methodology of prognostic research is however relatively underdeveloped. This is in contrast to its growing importance in clinical medicine. In the course, principles and methods of non-experimental prognostic research will be discussed. In lectures, practical exercises and discussion of examples, the practice of prognostic research in a clinical setting is addressed. Emphasis will be on design and statistical analysis of prognostic studies, construction and estimation of prediction rules and approaches to validation and generalization of research results. Problems with small datasets will be extensively discussed.
Programme:
Day 1 covers the principles of prognostic research and the interpretation of its results.
Day 2 covers the steps of prognostic model development, including predictor selection and the evaluation of model performance. This day includes a computer practical in which a prognostic model will be developed.
Day 3 is a continuation of day 2 and focuses on special issues in prognostic model development, including overfitting and shrinkage. Day 3 further focuses on the validation of prognostic models. This day includes a computer practical in which an advanced prognostic model will be developed and during which a prognostic model will be validated.
Day 4 deals with prognostic research with time to event data, e.g. Cox regression models, and addresses overlap and differences with regard to general linear models. In the afternoon there will be a practical to develop a prognostic model based on time to event data. The day concludes with a lecture about a case study.
Day 5 addresses the reporting of prognostic research (TRIPOD). Additionally, there will be a Q&A session, followed by the computer exam in the afternoon.
Literature/study material used:
-
Mandatory for students in own Master’s programme:
MIght be for a specialization programme of Epidemiology & Epidemiology Postgraduate
Optional for students in other GSLS Master’s programme:
Yes
Prerequisite knowledge:
Introduction to Epidemiology
Study Design
(Introduction to Statistics)
Classical Methods in Data Analysis
Modern Methods in Data Analysis
Clinical Epidemiology (preferred)
|
 |
|