Clinical data science can be defined as the scientific field, which turns healthcare data into clinically useful applications. This course will introduce the disciplines involved in the full value chain of clinical data science, covering the transformation of data to model and to applications, with an aim of giving an overview and understanding of the processes, rather than how to perform them. The course is organized into three major themes:
1) Data sources: The first part of the course covers the management and collection of data in structured form from both public sources, national registries and case report forms designed for a study, or from unstructured free text in patient journals using natural language processing We will introduce both how to access data, how to ensure privacy concerns (GDPR) are taken into account and how to make your own data useable for others (FAIR principles).
2) Modelling: The second part of the course teaches how to transform the collected data from possibly multiple sources to input for a predictive model, and how to train and validate a model using techniques such as classification, regression, or clustering. We will introduce the concept of explainable AI, and how to make predictions by an algorithm transparent, so the user can understand the basis of the recommendations. Finally, we will discuss the ethical concerns around using AI to guide treatment of patients.
3) Hands-on: The final part of the course deals with turning a validated model into a clinical decision support system to strengthen operational excellence in value-based health care. Throughout the course the participants will work with their own ideas for a decision support system, and relate it to the presented topics, culminating in designing a mock-up on the final day of the course.
- Prerequisites: Experience with collecting and analyzing health care data.
- Literature: Kubben, P., Dumontier, M., Dekker, A. (editors) Fundamentals of Clinical Data Science. Springer Open, 2019. Available online at: link
- Evaluation: The participant must present a mock-up of a decision support tool, covering a clinical problem related to their own area of research.
Louise Pape-Haugaard, Associate Professor, lph@hst.aau.dk
- ECTS: 3
- Time: 22-24 June 2021 8.30 - 16.00
- Place: Auditorium B, Forskningens Hus, Sdr. Skovvej 15
- Zip code: 9000
- City: Aalborg
- Number of seats: 30
- Deadline: 1 June 2021
Important information concerning PhD courses: We have over some time experienced problems with no-show for both project and general courses. It has now reached a point where we are forced to take action. Therefore, the Doctoral School has decided to introduce a no-show fee of DKK 3.000 for each course where the student does not show up. Cancellations are accepted no later than 2 weeks before start of the course. Registered illness is of course an acceptable reason for not showing up on those days. Furthermore, all courses open for registration approximately four months before start. This can hopefully also provide new students a chance to register for courses during the year. We look forward to your registrations.
- Teacher: Rasmus Froberg Brøndum
- Teacher: Martin Bøgsted
- Teacher: Louise Pape-Haugaard
- Teacher: Jan Brink Valentin