The KMD team was present with two scientific contributions:
- 'When can I expect the mHealth user to return? Prediction meets time series with gaps' by Miro Schleicher, Rüdiger Pryss, Winfried Schlee and Myra Spiliopoulou: the new machine learning method analyses the behaviour of users towards an mHealth app, learns from the absence of data and predicts if and when a user will start using the app again.
- 'Discovering Instantaneous Granger Causalities in Non-stationary Categorical Time Series Data' by Noor Jamaludeen, Vishnu Unnikrishnan, André Brechmann, and Myra Spiliopoulou: the new machine learning method analyses the data of an auditory category learning experiment, and it identifies characteristic patterns that distinguish between learners and non-learners.
Myra Spiliopoulou, together with Panos Papapetrou (Univ Stockholm) also presented a tutorial on 'Machine learning for complex medical temporal sequences'. Her part was on 'Dealing with Missingness/Gaps'.
Nehmen Sie an unseren Laborexperimenten teil! Participate in our Lab experiments!
Wir führen am Samstag, 11. Juni ab 18Uhr, Mitmachexperiment im Labor 021 durch.
Anne Rother's paper, "Virtual Reality for Medical Annotation Tasks – A Systematic Review", has been accepted in Frontiers.
On 12.04.2022 at 13:00 s.t. in room G10-337.
We will present topics for:
- Scientific Team Projects (Master)
- IT-Softwareprojects (Bachelor)
UPDATE 12 April:
Slides of topics:
- Myra Spiliopoulou (includes administrative information)
- Uli Niemann
- Christian Beyer (password-protected)
Application deadline: 21 April 2022 12:00.
In this tutorial, we focus on sequential forms of health-related data – spatial trajectories, panel data from longitudinal studies, time series signals (such as ECGs), event sequences (such as sequences containing EHR events) and mHealth data. We elaborate on the questions that medical researchers and clinicians pose on those data, and on the instruments they use. We elaborate on what questions are asked with those instruments, on what questions can be answered from those data, on ML advances and achievements on such data, and on ways of responding to the medical experts’ questions about the derived models. Furthermore, we emphasize the need for interpretable and explainable models that can inspire trust and facilitate informed decision making. Towards this goal we elaborate on actionable models and counterfactual explanations for sequential medical data, and discuss how to apply them for the interpretation of black-box models, such as deep learning architectures.
Anne Rother received the "Rudolf Kruse Award" (student research award) 2021. Congratulations!
Anne Rother, Uli Niemann, Tommy Hielscher, Henry Völzke, Till Ittermann, and Myra Spiliopoulou (2021). Assessing the difficulty of annotating medical data in crowdworking with help of experiments. PLOS ONE 16(7): e0254764. https://doi.org/10.1371/journal.pone.0254764
This semester, the KMD lab is offering topics for teamprojects.
Goal of the teamprojects is to enable students in solving complex real tasks in teamwork. In doing so, they use and occasionally extend methods they already learned in their studies thus far. They are exposed to the data science challenges of business understanding, of data preparation and of communicating the results to an application expert.
The application deadline is Oct. 28, 12:00.
More information and registration on Moodle/E-Learning: https://elearning.ovgu.de/course/view.php?id=11620