PV287 Artificial Intelligence and Machine Learning in Healthcare

Faculty of Informatics
Spring 2025
Extent and Intensity
1/1/0. 2 credit(s) (plus extra credits for completion). Type of Completion: k (colloquium).
In-person direct teaching
Teacher(s)
doc. Mgr. Bc. Vít Nováček, PhD (lecturer)
Guaranteed by
doc. Mgr. Bc. Vít Nováček, PhD
Department of Machine Learning and Data Processing – Faculty of Informatics
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics
Prerequisites
Basic knowledge of Python programming is desirable, but not essential. References for optional self-study:
- https://www.edx.org/course/cs50s-introduction-computer-science-harvardx-cs50x,
- https://www.edx.org/course/python-for-data-science-2.

Similarly, it wouldn’t hurt to have some minimal prior knowledge of life sciences. References for optional self-study:
- https://www.fi.muni.cz/~novacek/courses/pv287/resources/hunter-molecular-biology-for-computer-scientists.pdf,
- Section I of https://www.fi.muni.cz/~novacek/courses/pv287/resources/katzung-intro-to-pharma.pdf,
- slightly outdated but still relevant https://www.fi.muni.cz/~novacek/courses/pv287/resources/shortliffe-computational-medicine.pdf,
- more up to date https://www.nejm.org/doi/10.1056/NEJMra1814259 (an article on machine learning in medicine) or https://doi.org/10.1098/rsif.2017.0387 (a survey on deep learning in biology and medicine).
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
The capacity limit for the course is 15 student(s).
Current registration and enrolment status: enrolled: 0/15, only registered: 0/15, only registered with preference (fields directly associated with the programme): 0/15
fields of study / plans the course is directly associated with
Course objectives
The course provides a broad overview of the fields of biomedical and health informatics. The teaching methods are project-driven and research-oriented, with emphasis on reflecting the specific backgrounds and individual preferences of the students (including their possible scheduling restrictions). A special emphasis is put on learning how to use state-of-the-art Artificial Intelligence and machine learning techniques for tackling practical challenges in biology and medicine. We will focus on several representative use cases motivated by the real needs of life scientists and clinicians to illustrate the societal impact computer science can have in these fields. Perhaps most importantly, however, the course aims at bootstrapping an interdisciplinary community of young professionals who can deliver new results in this exciting field that are both technically sound and practically grounded.
Learning outcomes
Upon successful completion of the course, the students will be able to:
● name and explain the key reasons for applying AI in biomedical informatics and healthcare;
● name and explain the main challenges that complicate applying AI in biomedical informatics and healthcare;
● understand and apply a representative range of AI techniques in the context of life sciences;
● design and implement a specific biomedical AI application while working collaboratively in a multidisciplinary team;
● map real biomedical and/or clinical problems to possible solutions utilising state-of-the-art AI techniques;
● suggest an approach to validating the solutions using realistic benchmarks, data sets and qualitative methods based on expert committees.
Syllabus
  • ● Biomedical and healthcare informatics - an overview (2 introductory lectures)
  •  o Basic notions, the scope of the course.
  •  o Motivation, review of real-world challenges.
  •  o Historical overview of the field (from MYCIN to IBM Watson to AlphaFold).
  •  o Catching up with the basics (a crash/refresher course in life sciences for computer scientists and coding for life scientists).
  •  o Teaming up into groups of ca. 3 people for detailed analysis of papers on state-of-the-art biomedical AI approaches in areas like: classical and deep machine learning for biomedicine, relevant data sets, networked biomedical knowledge, biomedical knowledge integration, text mining and explainable AI. Each of the groups will also work on a semestral project based on their selected paper (replication and extension of the presented research).
  • ● Weekly progress update meetings between the teams and the teacher.
  • ● Up to two guest lectures about relevant topics from international experts.
  • ● Interim project presentations, hackathon no. 1 (fleshing out the project implementation plan, getting data, etc.)
  • ● Weekly progress update meetings between the teams and the teacher.
  • ● Final project presentations, colloqium/hackathon no. 2 - where to go next after what we've (un)learned so far?
Teaching methods
There will be some introductory lectures, but the bulk of the course is project-driven and research-oriented, focusing on teacher-moderated in-depth analysis of seminal papers that are motivating collaborative student projects. Progress gauging and teacher moderation will be realised within regular, individually organised update meetings, together with plenary hackathons and project presentations to the rest of the class.
Assessment methods
Assessment of the research paper analysis, evaluation of the collaborative projects as a whole, the students' individual contributions to them and the project presentations (in two stages - the intermediate and the final one).
Language of instruction
English
Further comments (probably available only in Czech)
The course is taught annually.
The course is taught: every week.
Teacher's information
The course is taught every year in the spring semester, on a weekly basis (unless the students mutually agree with the teacher on alternative arrangements that would better suit their individual schedules).
The course is also listed under the following terms Spring 2023, Spring 2024.
  • Enrolment Statistics (Spring 2025, recent)
  • Permalink: https://is.muni.cz/course/fi/spring2025/PV287