MED-BMS59
Prediction models and machine learning
Course infoSchedule
Course moduleMED-BMS59
Credits (ECTS)3
CategoryMA (Master)
Language of instructionEnglish
Offered byRadboud University; Faculty of Medical Sciences; Biomedische wetenschappen;
Lecturer(s)
PreviousNext 2
Lecturer
D. van As
Other course modules lecturer
Lecturer
dr. G.J. Hannink
Other course modules lecturer
Examiner
prof. dr. P.A.C. 't Hoen
Other course modules lecturer
Contactperson for the course
prof. dr. P.A.C. 't Hoen
Other course modules lecturer
Lecturer
prof. dr. P.A.C. 't Hoen
Other course modules lecturer
Academic year2022
Period
W44-B  (31/10/2022 to 31/08/2023)
Starting block
W44-B
Course mode
full-time
RemarksThursday and Friday for 4 weeks after the start of the period.
Registration using OSIRISYes
Course open to students from other facultiesYes
Pre-registrationYes
Pre-registration openfrom 20/06/2022 up to and including 10/07/2022
Waiting listYes
Placement procedureDone manually by Back Office
ExplanationDone manually by Back Office
Aims
After completion of the course, students are able to
  1. Explain the difference between etiologic and predictive research.
  2. Explain how regression and machine learning techniques relate to each other and can be used to build prediction models.
  3. Determine an appropriate machine learning strategy to answer a scientific question.
  4. Apply commonly used machine learning techniques to train and validate a model to answer a scientific biomedical question.
  5. Interpret commonly used measures for predictive performance.
  6. Explain how overfitting and underfitting occur.
Content
Prediction models are the cornerstone of personalized medicine. Yearly over 5,000 publications describe biomarker discovery, or prediction model development and validation. Unfortunately, the development and application of prediction models in medical science is often suboptimal. Moreover, advances in biostatistics and machine learning have led to new insights and opportunities for more accurate and useful prediction models that are able to tap into the wealth of (big) data that is collected in contemporary medical research and clinical practice. However, new technologies for prediction are difficult to apply without a solid understanding of the basic concepts underpinning prediction modeling.
During this course students will learn to address common problems in prediction modeling. First, they will learn the differences between etiological and prediction modelling, then understand the concepts of traditional epidemiological prediction models and learn how to build one themselves and from there learn the ‘machine learning language’ and how the methods compare to traditional epidemiological prediction models. Next, they will learn to create and evaluate a prediction model using advanced statistical techniques and machine learning algorithms (e.g. random forest, support vector machines). They will see and work with interesting biomedical problems such as establishing diagnoses based on large-scale clinical, imaging and molecular data. Guest lectures will show applications in stratification of patients for cancer therapy and artificial intelligence-supported diagnosis of cancers from radiological images.

Instructional modes:
Lectures, interactive lectures, computer assignments, online knowledge clips

Required prior knowledge
Prior to this course, participants should be able to:
  1. Design and critically evaluate an epidemiological study. More specifically they should be able to:
    1. Define the main epidemiologic study designs, i.e. cross-sectional, case-control, and cohort study.
    2. Define selection, information, and confounding bias.
    3. Explain how these biases arise in observational research.
    4. Define, calculate, and interpret measures for predictive performance:
  2. Perform hands-on R programming and be able to:
    1. Read in data and manipulate data objects
    2. Write loops and functions
    3. Perform logistic and linear regression in R.
    4. Basic matrix operations in R
If not at that level, take online DataCamp courses (or similar): https://learn.datacamp.com/courses/free-introduction-to-r (data types in R)
https://learn.datacamp.com/courses/intermediate-r  (conditionals, loops en functies)
https://learn.datacamp.com/courses/introduction-to-importing-data-in-r  (data importing)
https://learn.datacamp.com/courses/data-manipulation-with-dplyr (data selection and transformation)
Instructional modes
Working group

Tests
Written exam; open questions
Test weight80
Test typeOpen-ended exam
OpportunitiesBlock W44-B, Block W44-B

Report
Test weight20
Test typeReport
OpportunitiesBlock W44-B, Block W44-B