Hide-and-Seek Privacy Challenge: Synthetic Data Generation vs. Patient Re-identification

James Jordon, Daniel Jarrett, Evgeny Saveliev, Jinsung Yoon, Paul Elbers, Patrick Thoral, Ari Ercole, Cheng Zhang, Danielle Belgrave, Mihaela van der Schaar
Proceedings of the NeurIPS 2020 Competition and Demonstration Track, PMLR 133:206-215, 2021.

Abstract

The clinical time-series setting poses a unique combination of challenges to data modelling and sharing. Due to the high dimensionality of clinical time series, adequate de-identification to preserve privacy while retaining data utility is difficult to achieve using common de-identification techniques. An innovative approach to this problem is synthetic data generation. From a technical perspective, a good generative model for time-series data should preserve temporal dynamics; new sequences should respect the original relationships between high-dimensional variables across time. From the privacy perspective, the model should prevent patient re-identification. The NeurIPS 2020 Hide-and-Seek Privacy Challenge was a novel two-tracked competition to simultaneously accelerate progress in tackling both problems. In our head-to-head format, participants in the generation track (?hiders?) and the patient re-identification track (?seekers?) were directly pitted against each other by way of a new, high-quality intensive care time-series dataset: the AmsterdamUMCdb dataset. In this paper we present an overview of the competition design, as well as highlighting areas we feel should be changed for future iterations of this competition.

Cite this Paper

BibTeX
@InProceedings{pmlr-v133-jordon21a, title = {Hide-and-Seek Privacy Challenge: Synthetic Data Generation vs. Patient Re-identification}, author = {Jordon, James and Jarrett, Daniel and Saveliev, Evgeny and Yoon, Jinsung and Elbers, Paul and Thoral, Patrick and Ercole, Ari and Zhang, Cheng and Belgrave, Danielle and van der Schaar, Mihaela}, booktitle = {Proceedings of the NeurIPS 2020 Competition and Demonstration Track}, pages = {206--215}, year = {2021}, editor = {Escalante, Hugo Jair and Hofmann, Katja}, volume = {133}, series = {Proceedings of Machine Learning Research}, month = {06--12 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v133/jordon21a/jordon21a.pdf}, url = {https://proceedings.mlr.press/v133/jordon21a.html}, abstract = {The clinical time-series setting poses a unique combination of challenges to data modelling and sharing. Due to the high dimensionality of clinical time series, adequate de-identification to preserve privacy while retaining data utility is difficult to achieve using common de-identification techniques. An innovative approach to this problem is synthetic data generation. From a technical perspective, a good generative model for time-series data should preserve temporal dynamics; new sequences should respect the original relationships between high-dimensional variables across time. From the privacy perspective, the model should prevent patient re-identification. The NeurIPS 2020 Hide-and-Seek Privacy Challenge was a novel two-tracked competition to simultaneously accelerate progress in tackling both problems. In our head-to-head format, participants in the generation track (?hiders?) and the patient re-identification track (?seekers?) were directly pitted against each other by way of a new, high-quality intensive care time-series dataset: the AmsterdamUMCdb dataset. In this paper we present an overview of the competition design, as well as highlighting areas we feel should be changed for future iterations of this competition.} }
Endnote
%0 Conference Paper %T Hide-and-Seek Privacy Challenge: Synthetic Data Generation vs. Patient Re-identification %A James Jordon %A Daniel Jarrett %A Evgeny Saveliev %A Jinsung Yoon %A Paul Elbers %A Patrick Thoral %A Ari Ercole %A Cheng Zhang %A Danielle Belgrave %A Mihaela van der Schaar %B Proceedings of the NeurIPS 2020 Competition and Demonstration Track %C Proceedings of Machine Learning Research %D 2021 %E Hugo Jair Escalante %E Katja Hofmann %F pmlr-v133-jordon21a %I PMLR %P 206--215 %U https://proceedings.mlr.press/v133/jordon21a.html %V 133 %X The clinical time-series setting poses a unique combination of challenges to data modelling and sharing. Due to the high dimensionality of clinical time series, adequate de-identification to preserve privacy while retaining data utility is difficult to achieve using common de-identification techniques. An innovative approach to this problem is synthetic data generation. From a technical perspective, a good generative model for time-series data should preserve temporal dynamics; new sequences should respect the original relationships between high-dimensional variables across time. From the privacy perspective, the model should prevent patient re-identification. The NeurIPS 2020 Hide-and-Seek Privacy Challenge was a novel two-tracked competition to simultaneously accelerate progress in tackling both problems. In our head-to-head format, participants in the generation track (?hiders?) and the patient re-identification track (?seekers?) were directly pitted against each other by way of a new, high-quality intensive care time-series dataset: the AmsterdamUMCdb dataset. In this paper we present an overview of the competition design, as well as highlighting areas we feel should be changed for future iterations of this competition.
APA
Jordon, J., Jarrett, D., Saveliev, E., Yoon, J., Elbers, P., Thoral, P., Ercole, A., Zhang, C., Belgrave, D. & van der Schaar, M.. (2021). Hide-and-Seek Privacy Challenge: Synthetic Data Generation vs. Patient Re-identification. Proceedings of the NeurIPS 2020 Competition and Demonstration Track, in Proceedings of Machine Learning Research 133:206-215 Available from https://proceedings.mlr.press/v133/jordon21a.html.

Related Material