% 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{Sharafutdinov:910683,
      author       = {Sharafutdinov, Konstantin and Bhat, Jayesh S. and Fritsch,
                      Sebastian Johannes and Nikulina, Kateryna and E. Samadi,
                      Moein and Polzin, Richard and Mayer, Hannah and Marx, Gernot
                      and Bickenbach, Johannes and Schuppert, Andreas},
      title        = {{A}pplication of convex hull analysis for the evaluation of
                      data heterogeneity between patient populations of different
                      origin and implications of hospital bias in downstream
                      machine-learning-based data processing: {A} comparison of 4
                      critical-care patient datasets},
      journal      = {Frontiers in Big Data},
      volume       = {5},
      issn         = {2624-909X},
      address      = {Lausanne},
      publisher    = {Frontiers Media},
      reportid     = {FZJ-2022-04055},
      pages        = {603429},
      year         = {2022},
      abstract     = {Machine learning (ML) models are developed on a learning
                      dataset covering only a small part of the data of interest.
                      If model predictions are accurate for the learning dataset
                      but fail for unseen data then generalization error is
                      considered high. This problem manifests itself within all
                      major sub-fields of ML but is especially relevant in medical
                      applications. Clinical data structures, patient cohorts, and
                      clinical protocols may be highly biased among hospitals such
                      that sampling of representative learning datasets to learn
                      ML models remains a challenge. As ML models exhibit poor
                      predictive performance over data ranges sparsely or not
                      covered by the learning dataset, in this study, we propose a
                      novel method to assess their generalization capability among
                      different hospitals based on the convex hull (CH) overlap
                      between multivariate datasets. To reduce dimensionality
                      effects, we used a two-step approach. First, CH analysis was
                      applied to find mean CH coverage between each of the two
                      datasets, resulting in an upper bound of the prediction
                      range. Second, 4 types of ML models were trained to classify
                      the origin of a dataset (i.e., from which hospital) and to
                      estimate differences in datasets with respect to underlying
                      distributions. To demonstrate the applicability of our
                      method, we used 4 critical-care patient datasets from
                      different hospitals in Germany and USA. We estimated the
                      similarity of these populations and investigated whether ML
                      models developed on one dataset can be reliably applied to
                      another one. We show that the strongest drop in performance
                      was associated with the poor intersection of convex hulls in
                      the corresponding hospitals' datasets and with a high
                      performance of ML methods for dataset discrimination. Hence,
                      we suggest the application of our pipeline as a first tool
                      to assess the transferability of trained models. We
                      emphasize that datasets from different hospitals represent
                      heterogeneous data sources, and the transfer from one
                      database to another should be performed with utmost care to
                      avoid implications during real-world applications of the
                      developed models. Further research is needed to develop
                      methods for the adaptation of ML models to new hospitals. In
                      addition, more work should be aimed at the creation of
                      gold-standard datasets that are large and diverse with data
                      from varied application sites.},
      cin          = {JSC},
      ddc          = {004},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511) / SMITH -
                      Medizininformatik-Konsortium - Beitrag Forschungszentrum
                      Jülich (01ZZ1803M)},
      pid          = {G:(DE-HGF)POF4-5112 / G:(BMBF)01ZZ1803M},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {36387013},
      UT           = {WOS:000885597500001},
      doi          = {10.3389/fdata.2022.603429},
      url          = {https://juser.fz-juelich.de/record/910683},
}