SepsisExp: A Dataset of Patient Timelines with Expert Sepsis Labels

SepsisExp is a dataset based on data collected at the University Medial Centre in Mannheim, Germany (UMM). Timelines of 42 features were extracted from the Intellispace Critical Care and Anesthesia (ICCA) system by Philips (Eindhoven, Netherlands), and 1 demographic feature was extracted from the HIS system by SAP (Walldorf, Germany). Expert sepsis labels were collected using a electronic questionnaire implemented on a tablet computer.

Terms of Use

This data is available under a Creative Commons Attribution 4.0 International (CC BY 4.0). Please cite (Schamoni et al., 2022) if you use this data in your work.

Data and Code

The dataset is split into four partitions (A–D) that are used in the 4-fold cross validation experiments in (Schamoni et al., 2022). The code is available on https://github.com/StatNLP/sepens/.

For a more detailed description of the data construction process, see (Schamoni et al., 2022) and (Lindner et al., 2022).

Download

SepsisExp.tar.gz (v1, released 01/08/2022, 26MB, md5: bee934a56bef6d36214c3e7893d21a20)

Acknowledgments

This research has been conducted in project SCIDATOS (Scientific Computing for Improved Detection and Therapy of Sepsis), funded by the Klaus Tschira Foundation, Germany (Grant number 00.0277.2015).

Publications

  1. Shigehiko Schamoni, Michael Hagmann and Stefan Riezler
    Ensembling Neural Networks for Improved Prediction and Privacy in Early Diagnosis of Sepsis
    Proceedings of Machine Learning Research, 182, PMLR, Durham, NC, USA, 2022
    @inproceedings{schamoni2022,
      author = {Schamoni, Shigehiko and Hagmann, Michael and Riezler, Stefan},
      title = {Ensembling Neural Networks for Improved Prediction and Privacy in Early Diagnosis of Sepsis},
      booktitle = {Proceedings of the 6th Machine Learning for Healthcare Conference},
      year = {2022},
      city = {Durham, NC},
      country = {USA},
      volume = {182},
      series = {Proceedings of Machine Learning Research},
      month = {05--06 Aug},
      publisher = {PMLR},
      url = {https://www.cl.uni-heidelberg.de/~schamoni/publications/dl/MLHC2022_Ensembling.pdf}
    }
    
  2. H. A. Lindner, S. Schamoni, T. Kirschning, C. Worm, B. Hahn, F. S. Centner, J. J. Schoettler, M. Hagmann, J. Krebs, D. Mangold, S. Nitsch, S. Riezler, M. Thiel and V. Schneider-Lindner
    Ground truth labels challenge the validity of sepsis consensus definitions in critical illness
    Journal of Translational Medicine, 20(6), 27, 2022
    @article{lindner2022,
      author = {Lindner, H. A. and Schamoni, S. and Kirschning, T. and Worm, C. and Hahn, B. and Centner, F. S. and Schoettler, J. J. and Hagmann, M. and Krebs, J. and Mangold, D. and Nitsch, S. and Riezler, S. and Thiel, M. and Schneider-Lindner, V.},
      title = {Ground truth labels challenge the validity of sepsis consensus definitions in critical illness},
      journal = {Journal of Translational Medicine},
      year = {2022},
      volume = {20},
      number = {6},
      pages = {27},
      doi = {10.1186/s12967-022-03228-7},
      url = {https://doi.org/10.1186/s12967-022-03228-7}
    }