Improving Machine Learning Education During the COVID-Pandemic Using Past Computing in Cardiology Challenges.

During the COVID-Pandemic and the lockdown of universities, the need for stimulating, novel teaching methods was high, as most students were confined to their homes. For over 20 years, the annual PhysioNet/ CinC Challenges not only lead to technological advances for specijic problems, they have also proven repeatedly to be of immense value from an educational point of view. In this paper, we report results from the class "Artijicial Intelligence in Medicine Challenge", which was implemented as an online project seminar at TU Darmstadt and which was heavily inspired by the PhysioNet / CinC Challenge 2017 "AF Classijicationfrom a Short Single Lead ECG Recording". In particular, we show numeric results ofthe developed approaches on several datasets, highlight themes commonly observed among participants, and report the results from student evaluation. Several teams were able to implement approaches based on state- of- the-art algorithms achieving F1 scores above / close to 90 % on a hidden test-set of Holter recordings. Moreover, the self-assessment of the students reported a notable increase in machine learning knowledge.