% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Heumos:272953,
      author       = {Heumos, Lukas and Ehmele, Philipp and Treis, Tim and
                      Upmeier Zu Belzen, Julius and Roellin, Eljas and May, Lilly
                      and Namsaraeva, Altana and Horlava, Nastassya and Shitov,
                      Vladimir A and Zhang, Xinyue and Zappia, Luke and Knoll,
                      Rainer and Lang, Niklas J and Hetzel, Leon and Virshup,
                      Isaac and Sikkema, Lisa and Curion, Fabiola and Eils, Roland
                      and Schiller, Herbert B and Hilgendorff, Anne and Theis,
                      Fabian J},
      title        = {{A}n open-source framework for end-to-end analysis of
                      electronic health record data.},
      journal      = {Nature medicine},
      volume       = {30},
      number       = {11},
      issn         = {1078-8956},
      address      = {New York, NY},
      publisher    = {Nature America Inc.},
      reportid     = {DZNE-2024-01332},
      pages        = {3369 - 3380},
      year         = {2024},
      abstract     = {With progressive digitalization of healthcare systems
                      worldwide, large-scale collection of electronic health
                      records (EHRs) has become commonplace. However, an
                      extensible framework for comprehensive exploratory analysis
                      that accounts for data heterogeneity is missing. Here we
                      introduce ehrapy, a modular open-source Python framework
                      designed for exploratory analysis of heterogeneous
                      epidemiology and EHR data. ehrapy incorporates a series of
                      analytical steps, from data extraction and quality control
                      to the generation of low-dimensional representations.
                      Complemented by rich statistical modules, ehrapy facilitates
                      associating patients with disease states, differential
                      comparison between patient clusters, survival analysis,
                      trajectory inference, causal inference and more. Leveraging
                      ontologies, ehrapy further enables data sharing and training
                      EHR deep learning models, paving the way for foundational
                      models in biomedical research. We demonstrate ehrapy's
                      features in six distinct examples. We applied ehrapy to
                      stratify patients affected by unspecified pneumonia into
                      finer-grained phenotypes. Furthermore, we reveal biomarkers
                      for significant differences in survival among these groups.
                      Additionally, we quantify medication-class effects of
                      pneumonia medications on length of stay. We further
                      leveraged ehrapy to analyze cardiovascular risks across
                      different data modalities. We reconstructed disease state
                      trajectories in patients with severe acute respiratory
                      syndrome coronavirus 2 (SARS-CoV-2) based on imaging data.
                      Finally, we conducted a case study to demonstrate how ehrapy
                      can detect and mitigate biases in EHR data. ehrapy, thus,
                      provides a framework that we envision will standardize
                      analysis pipelines on EHR data and serve as a cornerstone
                      for the community.},
      keywords     = {Humans / Electronic Health Records / COVID-19: epidemiology
                      / SARS-CoV-2 / Pneumonia: epidemiology / Deep Learning},
      cin          = {AG Aschenbrenner},
      ddc          = {610},
      cid          = {I:(DE-2719)5000082},
      pnm          = {354 - Disease Prevention and Healthy Aging (POF4-354)},
      pid          = {G:(DE-HGF)POF4-354},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:39266748},
      pmc          = {pmc:PMC11564094},
      doi          = {10.1038/s41591-024-03214-0},
      url          = {https://pub.dzne.de/record/272953},
}