Seminar on Machine Learning in Health

Organizers

Dr. Maria Kalweit
Prof. Dr. Joschka Boedecker

Co-organizers

Dr. Gabriel Kalweit, Mehdi Naouar, Yannick Vogt, Lisa Graf

Description

Machine Learning, with its advanced algorithms and predictive modeling, has revolutionized numerous sectors, including healthcare. This seminar seeks to provide a focused examination of specific medical use cases. Participants will be invited to critically assess the inherent challenges associated with medical data, which often include limited sample sizes, noise, missing values and potential biases, and will explore state-of-the-art Machine Learning methods which can help to address these very challenges.

The format is the following:

Introductory lecture: We will discuss general aspects of scientific presentations in the beginning and define the format of the seminar.

Phase I: Each participant will become an expert in one methodological core area by reading one or multiple research papers, which we will assign after the students express their interest. Then, the students will form teams in the respective core areas and discuss advantages and disadvantages of their papers together.

Phase II: The students will again form groups to discuss specific medical use cases in light of the methodological core areas. Each group in Phase II will consist of one expert from each core area.

At the end of the semester, there will be a (potentially open-door) mini-symposium, in which the students will present their findings in both a prepared talk and a poster session.

Course information

Details:	Course number: 11LE13S-7341-M Places: 12 NEXUS Lab on the ground floor of the new IMBIT building (Georges-Köhler-Allee 201). The meetings are in person.
Course Schedule:	Introduction: Thursday, October 19th, 2023, 9:30 - 10:30 Block Seminar: Friday, February 16th, 2024, 9:00 s.t. - 18:00 s.t.
Requirements:	Prior knowledge in Machine Learning and Deep Learning.
Selection Procedure:	Please register via HISInOne. Candidates are prioritised if they either are present at the introduction event or write a short motivational mail to Dr. Maria Kalweit until Sunday, October 22th 23:59am. The subject line should include [ML in Health]. After you have been confirmed, you will then bid on a topic as discussed in the introduction event.
Resources:	Poster guideline as pptx or pdf
ILIAS:	https://ilias.uni-freiburg.de/goto.php?target=crs_3273455&client_id=unifreiburg

Timeline

	Date	Done	Comment
Announcement paper list:	Monday, October 23th	✓	Topics are listed below
Paper Voting Deadline :	Tuesday, October 31th	✓	Assignments were announced via email!
First Meeting with Supervisors:	Friday, December 1st	✓	Please send a pdf of the poster draft via email until Thursday, November 30. We will meet in IMBIT, room 42 (1st floor behind the kitchen).
Poster Deadline:	Friday, December 15th	✓	We received all submissions. Thank you.
Announcement Medical Use Cases	Monday, January 8th	✓	Work in your team on the medical use case announced via email.
Second Meeting with Supervisors:	Friday, February 2nd	✓	Please send a pdf or pptx of the presentation draft until January 31st. We will meet in IMBIT, room 42 (1st floor behind the kitchen).
Slides Deadline:	Friday, February 9th	✓	We received all submissions. Thank you.
Block Seminar [Format: Symposium]:	Friday, February 16th		See program below. We meet at the NEXUS Lab (ground floor) of the new IMBIT building.

All deadlines are due at 11:59 PM GMT+2 (These are hard deadlines!).

Minisymposium

Date: Friday, February 16th
Location: NEXUS Lab, IMBIT

9:15 - 9:45
Intro “Applicable AI in Medicine”
Neurorobotics Lab

9:45 - 10:30
Cell-TADA: Cell Tracking and Analysis with Domain Adaptation

10:30 - 11:15
MultiBind - A three Factor Binding Affinity Predictor and Mutation Tool for Antibody Design

LUNCH BREAK

12:30 - 13:15
I EAT DELIRIUM - Interpretable, Efficient, Accessible and Trustworthy Delirium Prediction

13:15 - 13:45
Poster Session I: Interpretability & Efficiency

13:45 - 14:15
Poster Session II: Accessible AI & Trustworthy AI

14:15 - 14:30
Discussion

END

2nd Meeting with Supervisors

We will meet in IMBIT, room 42 (1st floor behind the kitchen) to discuss your presentation drafts and general questions.

Medical Use Case 1: Cell Tracking 9:15 - 10:15
Medical Use Case 2: Antibody Design 10:15 - 11:15
Medical Use Case 3: Delirium Prediction 14:00 - 15:00

1st Meeting with Supervisors

We will meet in IMBIT, room 42 (1st floor behind the kitchen) to discuss your poster drafts and general questions.

Category A: Interpretability 9:15 - 10:15
Category B: Efficiency 10:15 - 11:15
Category C: Accessible AI 12:30 - 13:30
Category D: Trustworthy AI 13:30 - 14:30

Grading

The final grade will be based on the poster presentation and oral presentation on Feburary 16. The two meetings with the supervisors will not be graded - in these meetings you get feedback from us which you can use to improve the final submissions. More details will be announced. Please make sure that you attend all meetings on-site, since this is mandatory to pass the seminar.

Presentations

Once the posters are created, we will work on specific medical use cases. Then, you will work in a team with experts of the different core areas (category A-D) to create an oral presentation with slides (we will have 3 oral presentations).

Posters

The poster assignment was announced via email. Everyone creates his or her own poster about his or her assigned paper, which he or she will then present at the mini-symposium in the poster session (we will have 12 posters in total). In your core area group (category A - D), we will shortly go over the corresponding topic and talk about all posters on December 1, so that all of you get an overview over the core area and to get feedback on your paper from the supervisors and the other students.

Voting

If you got accepted to the seminar, please send your priorities in an email to Maria Kalweit. The email should have the following form:

Subject line: [ML in Health – Paper Voting]

Text:

[Your Priority list]

The list should have decreasing order (highest priority at the top, lowest at the bottom). Please list all papers (12 entries, one line per paper ID). For example:

B.1
B.2
A.1
B.3
...

Please send the email until Tuesday, October 11:59PM the latest. Any emails received after this deadline cannot be considered in the voting process. We will do our best to accommodate your preferences and ensure that you are assigned papers that align with your interests.

Topics

Category A: Interpretability

Category B: Efficiency

B.1: CoTracker: It is Better to Track Together [Paper] [Website]
B.2: Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning
B.3: Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series

Category C: Accessible AI

C.1: Segment Anything [Paper] [Website]
C.2: PPI-Affinity: A Web Tool for the Prediction and Optimization of Protein−Peptide and Protein−Protein Binding Affinity [Paper] [Website]
C.3: Collaborative design and implementation of a clinical decision support system for automated fall-risk identification and referrals in emergency departments

Category D: Trustworthy AI