Program Overview

STTBML-01 Biomedical Machine Learning

Autumn semester 2025

• ECTS: 5
• Form of instruction: Classroom instruction
• Form of examination: Oral
• Language of instruction: English
• Level: Bachelor
• Location: Aarhus

Course content

The course covers the following topics:

• General introduction to machine learning, including train/test split, performance metrics, regression as baseline, Naive Bayes benchmark, (un)supervised learning, etc.
• Introduction to machine learning in healthcare technology, including special considerations, types of data, and examples of suitable techniques.
• Brief introduction to Double Diamond and NABC pitching.
• Methods for assessing whether problems in the field of healthcare technology can be suitably solved by means of machine learning.
• Methods for searching for machine learning frameworks suitable for specific problems.
• Machine learning examples, both general examples and examples specific to healthcare technology.
• Overview of selected advanced machine learning techniques and future perspectives.

Description of qualifications

Motivation

The healthcare system is under pressure due to increasing demands and diminishing resources. For instance, the number of patients typically increases at a faster pace than the supply of qualified health professionals. Therefore, service may be significantly improved through the use of additional automation in the healthcare system and in healthcare technologies. The use of machine learning, which is a modern approach to automation, is increasing, both in private companies and in the public sector. As a consequence, the demand for employees with specialist competencies in machine learning is rising and expected to continue to rise.

At the same time, machine learning is the subject of much hype, and many products, companies, and projects assume expectations, which often do not hold up in practice.

Thus, in order to ensure the future of the healthcare sector, we need to educate qualified healthcare technology engineers, who not only understand how to use machine learning in practice, but who are also able to provide guidance and counselling in where and when these techniques can and cannot be used.

Learning outcomes

When the course is completed, the students are expected to be able to:

• Explore and apply suitable machine learning techniques, code libraries, and development tools for proof-of-concept solutions to practical tasks and for projects in the field of healthcare technology.
• Compare and assess the applicability of different machine learning frameworks, data, and techniques when analysing practical problems in the field of healthcare technology.
• Enter into constructive and informed dialogue about machine learning from a healthcare-technological perspective.
• Present the results of analysis, design, and/or implementation of machine learning in healthcare technology through brief and concise oral pitches.

Academic prerequisites

• 60 ECTS passed on a relevant education at Aarhus University

Language of instruction

• English

Hours - week - period

• Hours: 14x4 lectures
• Week: 4 h/week
• Period: 14 weeks

Type of course

• Ordinary, Exchange

Primary programme

• Bachelor's Degree Programme in Healthcare Technology

Related programmes

• Bachelor's Degree Programme in Software Technology

Department

• Department of Electrical and Computer Engineering

Faculty

• Technical Sciences

Location

• Aarhus

Maximum number of participants

• None

STADS UVA code

• 28523PU013

Teaching

• Form of instruction: Classroom instruction
• Instructor: Henrik Daniel Kjeldsen, Institut for Elektro- og Computerteknologi - Biomedical Engineering - Edison
• Course coordinator: Henrik Daniel Kjeldsen, Institut for Elektro- og Computerteknologi - Biomedical Engineering - Edison

Literature

• Not specified

Examination

• Form of examination: Oral
• Form of co-examination: Internal co-examination
• Assessment: 7-point grading scale
• Permitted exam aids: All
• Duration: 15 minute(s)

Requirements for taking the exam

• None

Comments

• Oral exam: The final result must be presented orally to the examiner (lecturer) and an internal co-examiner at a group exam (max. 4 students/group). The exam time is 15 minutes/student including time allocated for grading and entry/exit. Other groups are not permitted to attend the examination before their own examination. The exam presentation takes the form of a group NABC pitch with individual examination in the form of individual follow-up questions.
• Assessment: The oral group presentation and the individual questions are assessed as a whole with one overall grade.
• Re-examination: At the re-examination, the project must be presented as an individual NABC-pitch with following questions. The re-examination can either be based on the same project as in the ordinary exam or on a new project in agreement with the examiner.