| Dozent/in |
Ass.-Prof. Dr. Adrian Martinez de la Torre |
| Veranstaltungsart |
Vorlesung |
| Code |
HS251420 |
| Semester |
Herbstsemester 2025 |
| Durchführender Fachbereich |
Gesundheitswissenschaften |
| Studienstufe |
Master |
| Termin/e |
Fr, 24.10.2025, 08:15 - 16:00 Uhr, HS 7
Fr, 14.11.2025, 08:15 - 16:00 Uhr, 4.B55
Mi, 17.12.2025, 08:15 - 12:00 Uhr, HS 7 |
| Inhalt |
Day 1 – October 24:
- Introduction to Epidemiology in Sports and Rehabilitation
- Study Designs in Epidemiology:
o Cohort
o Case-Control
o Case-Crossover
o Self-Controlled Designs
- Biases in Sports Epidemiology: Selection, Information, and Confounding
o Equity and Representation in Epidemiology
- Statistical Fundamentals:
o Logistic and Cox Regression
o Introduction to Propensity Score Methods
o Hands-on group work with published datasets
Day 2 – November 14:
- Advanced Methods in Sports Epidemiology
o Longitudinal Data and Time-to-Event Analysis
o Effect Modification and Interaction
o Dealing with Missing Data
- Introduction to Machine Learning in Epidemiology
o Use cases: Predicting Return-to-Play in Football
o Models: Decision Trees, Random Forests, XGBoost
o Model Evaluation and Validation
- Group Project Work: Designing a mini-study or predictive model
Day 3 – December 17 (Half-Day):
- Group Project Presentations
- Peer Feedback & Wrap-Up Discussion
- Reflection on Real-World Implications and Research Careers in Sports Epidemiology |
| E-Learning |
Slides will be available on Moodle |
| Lernziele |
This intensive 2.5-day course provides students with foundational and advanced knowledge in sports epidemiology with a strong emphasis on rehabilitation contexts and data-driven decision-making. The course combines classical epidemiological study designs and statistical techniques with cutting-edge machine learning applications to predict outcomes such as return-to-play. Through real-world examples from elite sports (e.g., professional football), students will gain practical skills to conduct and interpret epidemiological studies in rehabilitation and sports health sciences.
By the end of the course, students will be able to:
- Understand the core principles of sports epidemiology and their application in rehabilitation.
- Design and critically evaluate cohort, case-control, case-crossover, and self-controlled studies.
- Identify and mitigate common biases in epidemiological research.
- Apply statistical methods such as regression modeling and propensity score matching.
- Use machine learning tools to develop predictive models related to return-to-play outcomes.
- Interpret sports epidemiological data in the context of real-world elite athlete case studies.
- Present and communicate research findings effectively. |
| Voraussetzungen |
- Basic knowledge of statistics and programmin in R is recommended but not necessary.
- Students should bring their own laptops with relevant software installed (RStudio).
- All datasets used are anonymized and for educational purposes only.
- Group presentations on December 17 are mandatory for course completion. |
| Sprache |
Englisch |
| Anmeldung |
https://elearning.hsm-unilu.ch/course/view.php?id=946 |
| Prüfung |
- Active participation in class and group work
- Completion of a short group project (presentation required)
IMPORTANT: In order to earn credits and participate at the exam registration via Uni Portal within the exam registration period is MANDATORY. As this is a block course the registration and deregistration runs from October 30 - December 10, 2025 . Further information: www.unilu.ch/en/study/courses-exams-regulations/health-sciences-and-medicine/exams/ |
| Abschlussform / Credits |
Participation, class and group work, group project / 3 Credits
|
| Hinweise |
Teaching methods:
- Interactive lectures with Q&A
- Group-based problem solving and mini-projects
- Case-based learning with real-world sports examples
- Hands-on statistical exercises using R
- Peer review and presentations |
| Hörer-/innen |
Nein |
| Kontakt |
adrian.martinez@unilu.ch |
| Material |
- Slides and lecture notes
- Datasets for analysis (e.g., anonymized football injury datasets)
- Code templates for statistical and machine learning models (in R)
- Case studies of well-known athletes' injury trajectories |
| Literatur |
Rothman, Kenneth J., Sander Greenland, and Timothy L. Lash. Modern epidemiology. Vol. 3. Philadelphia: Wolters Kluwer Health/Lippincott Williams & Wilkins, 2008.
Strom, Brian L., Stephen E. Kimmel, and Sean Hennessy. "Textbook of Pharmacoepidemiology."
Valle, X., Mechó, S., Alentorn-Geli, E., Järvinen, T. A. H., Lempainen, L., Pruna, R., Monllau, J. C., Rodas, G., Isern-Kebschull, J., Ghrairi, M., Yanguas, X., Balius, R., & la Torre, A. M. (2022). Return to Play Prediction Accuracy of the MLG-R Classification System for Hamstring Injuries in Football Players: A Machine Learning Approach. Sports medicine (Auckland, N.Z.), 52(9), 2271–2282. https://doi.org/10.1007/s40279-022-01672-5 |