The course Applications of Digital Health aims to teach students about the intersection between healthcare and technology in two parts. In the first part the students learn about different ways technology can support existing processes in healthcare or create new ways of prevention, diagnosis, treatment or monitoring of health conditions. In the second part of the course the students acquire fundamental knowledge on machine learning and how machine learning is used in healthcare. The students will learn to implement their own predictive models using different types of health data in Python.
The course consists of:
- Lectures: Build a strong theoretical base on digital health and machine learning.
- Applied Lectures: Learn how to apply this knowledge in Python, visit two research labs at the university, learn soft skills such as reading scientific papers and presenting.
- Lab Sessions: No frontal teaching, only interactive problem solving in Pythons assignments, Q&A sessions, presentation workshop and project coaching.
Grading
12 weeks of course. 6 hours of direct lecture per week plus independent work of the students. • Small Assignments (20%): The students have to hand in 4 Jupyter Notebooks with code exercises and questions about the code. Two of these small assignments are about basic Python skills and two small assignments are on Machine Learning in. The students are encouraged to work in groups, but everyone needs to hand in their own file.
o Grading: Pass or Fail.
o Goal: Learn Python.
• Paper Presentation (10%): The students are provided with scientific papers about applications of digital health (including e.g. VR technology for Anxiety treatment, AI-based dermatology screening, health monitoring with smartwatches,…). Each student has to pick a paper, read it carefully and teach the content to their classmates in a 10 minute presentation. The students additionally have to read one of their classmates papers and prepare questions to ask them after their presentation.
o Grading: Grade between 0-10 based on the presentation and answers to the questions.
o Goal: Practice paper reading and presenting
• Written Exam (30%): This classical assessment form aims to test the students knowledge on Digital Health and Machine Learning. The exam is 60 minutes and includes 5 questions on digital health and 5 questions on machine learning. The students receive a mock exam with examples of questions and there will be a Q & A session before the exam to answer open questions about the mock exam.
o Grading: Grade between 0-10 based on answers in the exam.
o Goal: Strengthen your theoretical knowledge
Finall Project (40%): In this project, the students will apply their machine learning knowledge to a medical dataset. They will work in groups of 3-4 students, where every group receives a different data set.
o Grading: Grade between 0-10 based on final presentation, a Jupyter notebook with code, and a final report.
o Goal: Combine everything the students have learned.
- Knowledge and good understanding of digital health data, technology, and applications.
- Ability to design digital health solutions, particularly in the fields of mobile healthand tele health.
- Ability to apply machine learning techniques to analyse different types of health data.
- Basic programming skills in Python, including reading and transforming health data with pandas and plotting health data with matplotlib.
- Machine learning skills in Python, including preprocessing, classifying, and evaluating health data in scikit-learn.
- Ability to read and summarize scientific papers
- Presentation skills
It’s beneficial to have either existing knowledge in a health-related or technology related field. There are no strict pre-requisites for this course.