Clinical Data Science (KDW)
1/2. Semester
5 ECTS | 4 SWS
Oral Exam (M)
Analyze Clinical Data with Machine Learning: Learn how to analyze large collections of electronic patient data using statistical and machine learning methods, apply R for implementation, and interpret the results to generate new medical insights.
Contents
- The growing availability of electronic clinical data has significantly expanded the opportunities to automatically analyze previously undiscovered medical relationships and generate new medical knowledge. Such analyses are often exploratory rather than hypothesis-driven and therefore differ from traditional statistical methods. The scientific use of routinely collected patient data also presents new challenges, including the integration of heterogeneous data structures and diverse clinical documentation formats. This course focuses on automated analysis methods for patient data. After providing an overview of established approaches to generating medical knowledge (including biostatistical foundations and study designs), the course introduces the principles and common characteristics of automated data analysis methods. Selected techniques and practical applications are then explored in greater depth, along with approaches for statistical evaluation. The course also includes a practical introduction to the R programming language. Through hands-on exercises, participants independently learn selected analytical methods, apply them to clinical sample datasets, and critically interpret the resulting findings.
Competencies
Students are able to
- explain the fundamental principles and classification of machine learning methods.
- understand the classification and characteristics of relevant clinical data.
- understand and apply the R programming language.
- implement R scripts to apply machine learning methods to patient data.
- review and validate the results of automated analyses of diverse clinical datasets.
Literature
- Han, Kamber, Pei: Data Mining - Concepts and Techniques (3rd ed.)
- An Introduction to R (http://cran.r-project.org/doc/manuals/R-intro.pdf)
- Kourou et al.: Machine learning applications in cancer prognosis and prediction (2015)
- Bellazzi and Zupan: Predictive data mining in clinical medicine: current issues and guidelines (2008)
Lecturer
Recommended Previous Knowledge
Module Details
| Semester |
1/2 |
| Lecture Language |
German |
|
Frequency
|
Not regularly
|
| Credit Points (ECTS)
|
5 |
| Course Coordinator |
Prof. Dr. Stefan Kraus |
| Duration |
1 Semester |
| Study Focus |
Medical Data Science (MDS)
|
|
Course Achievement
|
None |
|
Prerequisite for exam
|
Compulsory Assignment (PU) |
|
Exam
|
Oral Exam (M) |
Weekly Hours (SWS)
| Lecture |
3 SWS |
| Exercises |
1 SWS |
| Sum |
4 SWS |
Work Load
| Lecture |
60 h |
| Self Study |
30 h |
| Assignments |
40 h |
| Exam Preparation |
20 h |
| Sum |
150 h |
