Focus Group on Artificial Intelligence for Health
Duration: July 2018 – present
The International Telecommunication Union (ITU) and World Health Organization (WHO) Focus Group on "Artificial Intelligence for Health" (FG-AI4H; see project website) is establishing a platform on which AI applications for health can be rigorously evaluated against a system of standards. The Machine Learning group provides organizational and technical support to the focus group. For the latter, this includes guidance in the selection of representative training data for evaluation of AI algorithms and enhancing the interpretability and transparency of AI algorithms.
Project partners (not exhaustive):
International Telecommunications Union, World Health Organization, EPFL, The Lancet, ACM, REDDS Capital, CAICT.
Dähne, S., Bießmann, F., Samek, W., Haufe, S., Goltz, D., Gundlach, C., Villringer, A., Fazli, S., Müller, K.-R. (2015). Multivariate machine learning methods for fusing multimodal functional neuroimaging data. Proceedings of the IEEE, 103(9), 1507–1530.
Samek, W., Blythe, D., Curio, G., Müller, K.-R., Blankertz, B., Nikulin, V. (2016). Multiscale temporal neural dynamics predict performance in a complex sensorimotor task. NeuroImage, 141, 291–303.
Sturm, I., Lapuschkin, S., Samek, W., Müller, K.-R. (2016). Interpretable deep neural networks for single-trial EEG classification. Journal of Neuroscience Methods, 274, 141–145.
Bubba, T.A., Kutyniok, G., Lassas, M., März, M., Samek, W., Siltanen, S., Srinivasan, V. (2018). Learning the invisible: A hybrid deep learning-shearlet framework for limited angle computed tomography. Preprint at arXiv:1811.04602.
Horst, F., Lapuschkin, S., Samek, W., Müller, K.-R., Schöllhorn, W. (2018). What is unique in individual gait patterns? Understanding and interpreting deep learning in gait analysis. Preprint at arXiv:1808.04308.
Thomas, A., Heekeren, H., Müller, K.-R-., Samek, W. (2018). Interpretable LSTMs for whole-brain neuroimaging analyses. Preprint at arXiv:1810.09945.
Strodthoff, N., Strodthoff, C. (2018). Detecting and interpreting myocardial infarctions using fully convolutional neural networks. Preprint at arXiv:1806.07385.