Artificial Intelligence in Medicine 2019

University Poznan
The University of Poznan, in Poland venue of AIME'19.

The end of June 2019 I decided to attend Artificial Intelligence in Medicine (AIME'19) 

Differences AI in Medicine and AI in Education - in a nutshell.

AI in Medicine is not precisely my field of research but is a highly interesting related topic. The methods are different also the objectives. For instance, in medicine, as compared to Education there is hardly any feedback. Most of the effort is spent into predictive modelling, e.g. to diagnose cancer among a population. The main issue in these cases, is the highly unbalanced datasets. Treating this unbalanced datasets can lead to some very silly mistakes, like the one discovered by my fellow colleague Gilles Vandewiele. 

Some applications of AI in medicine are very much similar to the field of education. In particular, medicine is a subject which is highly multimodal that meaning that it privileges physical world interaction. Very interesting was the approach used by Hassan Fawaz on Automatic alignment of surgical videos using kinematic data


Doctoral Consortium Presentation

I attended the Doctoral Consortium where I presented my last research project, the Multimodal Tutor for CPR. This was actually my 4th doctoral consortium (LAK'17, AIED'17, AIED'18, AIME'19) so was particularly confident presenting my PhD project. This, however, did not save me from some "not-so-constructive" comments on my work. 

But, to be honest, I was not very much hit like the first and the second time I have attended, I rather took all actionable feedback I could into account and brought it with me home.

I believe attending a DC is always a cool idea if you are PhD because 1) you can report on the progress of your PhD and get some feedback, 2) you don't need to have results but still get feedback on the methodology, 3) you typically get a scholarship to attend the conference.

If you are looking for even more reason to attend a DC check the blog post by the fellow researcher Shibani - Preparing for the DC


Published by Daniele Di Mitri

Daniele Di Mitri is a research group leader at the DIPF - Leibniz Institute for Research and Information in Education and a lecturer at the Goethe University of Frankfurt, Germany. Daniele received his PhD entitled "The Multimodal Tutor" at the Open University of The Netherlands (2020) in Learning Analytics and wearable sensor support. His research focuses on collecting and analysing multimodal data during physical interactions for automatic feedback and human behaviour analysis. Daniele's current research focuses on designing responsible Artificial Intelligence applications for education and human support. He is a "Johanna Quandt Young Academy" fellow and was elected "AI Newcomer 2021" at the KI Camp by the German Informatics Society. He is a member of the editorial board of Frontiers in Artificial Intelligence journal, a member of the CrossMMLA, a special interest group of the Society of Learning Analytics Research, and chair of the Learning Analytics Hackathon (LAKathon) series.

Leave a Reply

Your email address will not be published. Required fields are marked *