About the project
Background
Artificial intelligence (AI) methods and machine learning in particular are playing an increasingly important role in medicine, as they have the potential to utilize the increasing amount of available data for more efficient diagnostic and therapeutic procedures. Unlike in other applications, however, it is not only the "content-related performance" that plays a decisive role with regard to medical use, but also the interpretability, individualization and approval issues.
Own priorities
In various projects, we are working on the use and further development of artificial intelligence methods to improve medical care. Particular attention is paid to the above-mentioned aspects of interpretability, individualization and approval issues. Our own work covers feature extraction, selection and classification/clustering. Specific examples are
- the automated evaluation of sleep phases,
- therapy recommendation systems,
- the early detection/prediction of medical emergencies and
- ECG processing.
Literature
(Exemplary selection of own works on the topic)
- F. Gräßer, S. Beckert, D. Küster, J. Schmitt, S. Abraham, H. Malberg, and S. Zaunseder, "Therapy Decision Support Based on Recommender System Methods," J. Healthc. Eng, vol. 2017, p. 8659460, 2017.(Opens in a new tab)
- T. Mar, S. Zaunseder, J. P. Martínez, M. Llamedo, and R. Poll, "Optimization of ECG classification by means of feature selection," IEEE Trans. Biomed. Eng, vol. 58, no. 8, pp. 2168-2177, Aug. 2011.(Opens in a new tab)
- S. Zaunseder, R. Huhle, and H. Malberg, "CinC Challenge - Assessing the Usability of ECG by Ensemble Decision Trees," in Proceedings of Computing in Cardiology, Volume 38, 2011.(Opens in a new tab)