Introduction to Medical Data Science (Data-Driven Medicine: DDM1)

This course aims to introduce medical students to the basics of data science, the importance of data, aspects of data reusability and how best to prepare data for data mining.

The first session will be a lecture providing practical information on how Biomedical Data can be preprocessed in order to prepare data mining processes, i.e. to make the data (re-)usable for Data Driven Medicine (DDM).

The lecture concludes with a brief introduction to coding with the programming language python.

As an optional homework the students can implement presented methods in python. At the beginning of the second session, the solution of the homework will be discussed.

Afterwards, the presented methods will be implemented on a biomedical data set in a hands-on exercise using the software tool KNIME.

To discover the full DDM pipeline DDM 2, 3 and 4 should be attended as well.

Teaching machines how to make a decision : Supervised Machine Learning (Data-Driven Medicine: DDM2)

This course provides both theoretical and practical information on how knowledge can be generated from Biomedical Data using Supervised Machine Learning (ML) methods in the field of Data Driven Medicine (DDM).

The first session will be a lecture on Supervised ML approaches, which ends with a brief introduction to coding with the programming language python.

As an optional homework the students can implement presented methods in python.

At the beginning of the second session, the solution of the homework will be discussed. Afterwards, the presented methods will be implemented on a biomedical data set in a hands-on exercise using the software tool KNIME.

To discover the full DDM pipeline DDM 1, 3 and 4 should be attended as well.

How machines can self learn: Unsupervised Machine Learning (Data-Driven Medicine: DDM3)

This course provides both theoretical and practical information on how knowledge can be generated from Biomedical Data using Unsupervised Machine Learning (ML) methods in the field of Data Driven Medicine (DDM).

The first session will be a lecture on Unsupervised ML approaches, which ends with a brief introduction to coding with the programming language python.

As an optional homework the students can implement presented methods in python.

At the beginning of the second session, the solution of the homework will be discussed.

Afterwards, the presented methods will be implemented on a biomedical data set in a hands-on exercise using the software tool KNIME.

To discover the full DDM pipeline DDM 1, 2 and 4 should be attended as well.

Diagnosing  AI algorithms: Visualisation and Evaluation (Data-Driven Medicine: DDM4)

In two sessions this course theoretically and practically shows how the results of data mining in the field of Data Driven Medicine (DDM) can be evaluated and visualised.

The first session will be a lecture on evaluation approaches and visualisation techniques, which ends with a brief introduction to coding with the programming language python.

As an optional homework the students can implement presented methods in python.

At the beginning of the second session, the solution of the homework will be discussed.

Afterwards, the presented methods will be implemented on a biomedical data set in a hands-on exercise using the software tool KNIME.

To discover the full DDM pipeline DDM 1, 2 and 3 should be attended as well.

Ethical aspects of Medical AI applications

The course focuses on ethics of AI/data science with specific focus on medical applications.

It aims to raise awareness on the basic principles of AI ethics and the ethical guidelines, specifically for medical applications.

It will also focus on issues such as data privacy, consent and bias as manifested in health care use cases.

Medical Image processing

The course will cover standard imaging methods used in hospitals today -- i.e., x-ray, CT, MRI. The basic principles, instrumentation, and applications of each imaging modality will be presented in interactive lectures. Using AI methods makes it possible for efficient interpretation and evaluation of digital images and health data. This course also will introduce various machine learning algorithms, which are well applied in the medical domain. We will mainly focus on deep neural networks, which are widely employed in the following tasks, image classification, image synthesis, semantic segmentation, and instance segmentation. To better understand, the seminar will explain the working mechanisms of the structures of different neural networks, such as forward neural networks, convolutional neural networks, residual networks, and U-Net. And students will have the opportunity to run code experiments. Frequently-used metrics will also be included to evaluate the performance of deep learning methods.

Data Analytics with Python for Medical Doctors

The objective of this course is to provide the basics of exploratory data analysis techniques in Python, including data exploration, data visualization, and data quality.

Throughout this course, you will gain hands-on experience with available tools and libraries that help you to conduct initial investigations on your data in order to discover patterns, identify anomalies, test hypotheses, and verify assumptions using summary statistics and graphical representations.

Semantic Interoperability in Health

This is an introductory module to help students acquire a basic understanding of interoperability and semantics and unveil the concepts of FAIR Data that aim at improving Findability, Accessibility, Interoperability and Reuse of data.

Due to the increasing volume and complexity of data, there is need for leveraging automation in acquiring, processing and managing data from different sources and a key aspect to this is interoperability.

In the course we address a variety of subjects related to semantics including conceptual models and ontologies with applications to medical use cases.

MedTech: Medical Technology-based entrepreneurship and innovation

This is an interactive, experiential learning course to help medical students acquire basic competence and cope with the challenges and the opportunities faced by entrepreneurs in starting or growing a MedTech startup.

The students are supported to explore case studies and develop content and strategies that are necessary for MedTech entrepreneurs to be familiar with.

Students will be offered the necessary support to work in groups or independently for acquiring hands-on experiences related to the various aspects of launching a MedTech as well as for expanding their initial ideas into viable business opportunities.

Generating knowledge from data using machine learning (ML) is becoming increasingly important in every conceivable scientific field.

To provide an introduction to data science, this course will cover various ML methods, including supervised and unsupervised methods, as well as techniques for evaluating and visualising the results.

With a focus on practical implementation, all approaches presented will be briefly introduced theoretically and then implemented using the programming language python.

Prior knowledge of programming is not required.

The course aims to familiarize the students with the basic concepts of the domain and underline the challenges posed by the explosion of data-driven applications using Artificial Intelligence (AI) in recent years.

Topics that will be covered range from an introduction to data driven AI and Machine Learning, artificial agents, privacy and consent, bias and discrimination, environmental and social aspects of AI applications as well as the presentation of guidelines and frameworks regarding Ethical / Trustworthy / Responsible AI.

The module is meant to present relevant issues in an interdisciplinary perspective.

It is an introductory course and assumes no previous knowledge of either Ethics or AI.