Artificial intelligence and computational medicine

Teaching semester

First four weeks of the spring term.

Objectives and Content

The objective and content of the course addresses

• The computational mindset, machine learning and AI in future medicine - pros et cons
• A guided tour of some mathematical and statistical modelling techniques in biomedical and clinical applications. Examples and demonstrations will be related to in vivo imaging and integrated quantitative physiology, imagingderived biomarkers, omics data, and sensor data.
• Operational principles of selected sensors and measurement devices in biomedical research and clinical practise - from smartphones to MRI scanners.
• The concepts of "big data", "data analytics", "machine learning", and "deep convolutional neural networks" with examples from personalized and predictive medicine.
• Throughout the course, the students will use principles and tools from numerical programming, data analysis, and scientific computing for medical applications. This will provide an introduction to e.g. R, Python, and Jupyter notebooks, and "the cloud" for data storage and computations.
• The concepts and importance of "open science", "data sharing", and "reproducible research".

Learning Outcomes

Knowledge

• Is able to explain basic operational principles of selected sensors and measuring devices in biomedical research and clinical practise
• Is knowledge-able about the concepts of"big data", "data analytics", "machine learning", and "deep convolutional neural networks" and provide examples from personalized and predictive medicine.
• Is knowledge-able about the concepts and importance of "open science", "data sharing", and "reproducible research".

Skills

• Can find and use modern software tools for data analysis, visualization and reporting (e.g. figure / graphics production with Jupyter notebooks).
• Can communicate selected methods and software packages where these methods are implemented and explain their relevance to medical research and clinical practice.

General competence

• Acknowledging the importance of mathematical models and computations in the analysis and understanding of complex physiological systems and disease processes, and the need of crossdisciplinary collaborations in future medicine.

Required Previous Knowledge

Preferably passed the first two study years in medical school, or first two years in engineering school within the disciplines computer science, electrical engineering, mechanical engineering, chemical engineering or first two study years in the bachelor program of mathematics, informatics, physics, chemistry, or physics.

Recommended Previous Knowledge

For the medical students, recommended previous knowledge includes organ physiology, anatomy, and cell biology / molecular biology at the level of passed second year into the medical curriculum, and having curiosity/interest in technology, mathematics, and computer science. Medical students on the research track are welcome to take the course. For the engineering students and students in mathematics, informatics, or physics, recommended previous knowledge includes calculus / linear algebra and computer programming at the level of the second year of engineering school or bachelor programs, together with an interest in biological and medical phenomena and applications.

Access to the Course

Students enrolled at the Faculty of Medicine, or Faculty of Mathematics and Natural Sciences, UiB (or other university) and engineering students at the Western Norway University of Applied Sciences (or other engineering college, e.g. Erasmus student). Students external to UiB will be enrolled as guest student for the course.

Note that you have to sign up by email to elektiv@med.uib.no. There is a deadline for signing up. Contact elektiv@med.uib.no for information about this.

Teaching Methods and Extent of Organized Teaching

The teaching methods consist of "blended learning" and "flipped classroom":

• Two days of introductory and motivational lectures incl. demonstrations. Students bring their own laptop.
• E-learning modules (pre & per & post course) with focus on the learning outcomes. Comprises thematic MCQs and reflective questions. Open-ended questions prompt learners to explore their thoughts and opinions while testing their comprehension.
• Two assignments with peer assessment: (i) one assignment related to modern e-infrastructure of computational science (computing environments / IDE, data repositories, source code versioning systems [GitHub] etc.), (ii) one assignment "in tandem" being related to a specific topic within (bio)medicine among several predefined choices, where preferably one engineering student and one medical student work together. This project will be presented orally at one of the course meetings.
• Four meet-ups (one TBL session) / group meetings with lecturers / TAs.
• Digital final exam.

The course will assume the students have their own laptop (or borrow one).

Compulsory Assignments and Attendance

Two compulsory assignments and an oral presentation, with a peer assessment component. Compulsory assignments / oral presentation must be approved ("pass") before the final digital exam.

Forms of Assessment

Final MCQ home exam.

Grading Scale

Pass / No pass

Subject Overlap

BMED360/HUFY372 (2 ECTS)

Course Evaluation

Written evaluation using electronic/digital evaluation tool.