Sonja Aits, Faculty of Medicine, Lund University (course coordinator)
Mattias Ohlsson, Faculty of Science, Lund University
Teaching assistants: Rafsan Ahmed, Salma Kazemi Rashed
Artificial intelligence is rapidly entering medicine and life science research as well as pharmaceutical industry and health care institutions. It is also increasingly used in environmental sciences. This introduction course will give an overview over artificial intelligence concepts and methods and over current and future applications of artificial intelligence in medicine and life sciences. Societal, ethical and legal challenges will also be addressed. In addition, students will hear about ongoing research in this area at Lund University and develop a project plan for an artificial intelligence research project in their own research domain. This is the first course in the new course package on "Artificial Intelligence in Medicine and Life Science" and will not have any programming exercises. There are several complementary in-depth courses with practical exercises, each focusing on different types of data.
The course is targeted at PhD students, researchers and other professionals in medicine, life science, environmental science, engineering, maths or computer science or related fields.
The official course plan outlining the course content, learning goals, etc.
https://www.compute.lu.se/fileadmin/compute/documents/course_plans/NTF012F-Eng.pdf
Course days are Dec 12, 13, 14, 15, 2023.
Dec 12
| Time | Title | Teacher | Material |
|---|---|---|---|
| 09:00 – 10:00 | Welcome and introduction round | Sonja Aits | slides |
| Ca 09:45 – 10:15 | Break | ||
| 10:15 – 11:30 | Introduction: what is AI and how can it be used in medicine and life sciences? | Sonja Aits | slides |
| 11:30 – 12:00 | Data types and sources | Sonja Aits | slides |
| 12:00 – 13:00 | Lunch break | ||
| 13:00 – 15:00 | General AI Concepts and Tasks | Mattias Ohlsson | slides |
| Ca 14:00 – 14:30 | Break |
Dec 13
| Time | Title | Teacher | Material |
|---|---|---|---|
| 10:30 – 12:00 | Computer vision in medicine and life science | Sonja Aits | slides |
| 12:00 – 13:00 | Lunch break | ||
| 13:00 – 16:00 | General AI Concepts and Tasks II | Mattias Ohlsson | slides |
| Ca 14:00 – 14:30 | Break |
Dec 14
| Time | Title | Teacher | Material |
|---|---|---|---|
| 09:00 – 11:00 | Natural language processing in medicine and life science | Sonja Aits | slides |
| 11:00 – 11:30 | Break | ||
| 11:30 – 12:00 | Developing your AI project | Sonja Aits | slides |
| 12:00 – 13:00 | Lunch break | ||
| 13:00 – 16:00 | Independent project work | project template |
Dec 15
| Time | Title | Teacher | Material |
|---|---|---|---|
| 09:00 – 09:30 | Societal, ethical and legal implications of AI | Sonja Aits | slides |
| 09:30 – 10:45 | Discussion of societal, ethical and legal implications of AI | Sonja Aits, teaching assistants | slides |
| 10:45 – 11:15 | Break | ||
| 11:15 – 12:00 | AI research in practice: project design, problems and trouble shooting in 4 ongoing research projects in the Cell death, Lysosomes and AI group at Lund University | Sonja Aits | slides |
| 12:00 – 13:00 | Lunch break | ||
| 13:00 – 16:00 | Independent project work | project template |
Project presentations and oppositions which serve as examinations are on Jan 22 and 23, 2024
It is not mandatory to attend all parts of the course to receive a pass grade as the course material will be shared and can be studied independently. However, if you are going to miss more than half a day, please get in contact with the course leader. Attendance at the examination is mandatory but if needed, an alternative examination date can be set up.
Grades are pass/fail. The examination consists of an individual project (home assignment) and opposition.
You are encouraged to discuss the course materials and your project ideas with your classmates. However, all work you submit must be your own. Shared projects or re-submission of prior course or research work you have created yourself is not allowed.
This is encouraged:
- Getting feedback on project ideas from fellow course members, friends or colleagues
- Discussing general approaches to solving the tasks with others
- Looking at reserach articles, tutorials or github repos to understand how others have approached similar tasks
- Re-using graphical elements (e.g. diagrams, cartoons) you or others have created in other contexts for the introduction part of your presentation (with attribution)
This is is not allowed and constitutes plagiarism:
- Submitting the same or highly similar presentation, report, review or code as another course member. A mere change of the research question is not sufficiently different either if the project strategy is otherwise identical.
- Copying all or almost all presentation content from other sources or from one of your previous courses, thesis works or research projects
- Copying text sections for your report or slides for your presentation from other sources
Basically, follow common sense and sound scientific and educational practice. If in doubt, please ask!
If you do not have your own dataset, many can be found here:
https://datasetsearch.research.google.com/
https://archive.ics.uci.edu/ml/index.php
https://www.kaggle.com/datasets
https://bbbc.broadinstitute.org/
To help design your project, you are expected to read at least one research article related to your projects. Suitable articles can for example be found on:
https://www.ncbi.nlm.nih.gov/pubmed/
For those of you who want to deepen your knowledge after the course, you can find additional material on https://github.com/Aitslab/training and https://github.com/COMPUTE-LU.
This repo is made public as an open educational resource. All material in it is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. If you teach a course based on this material, we would appreciate your feedback so we can improve it further.