% 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{ESamadi:909773,
author = {E. Samadi, Moein and Kiefer, Sandra and Fritsch, Sebastian
Johaness and Bickenbach, Johannes and Schuppert, Andreas},
title = {{A} training strategy for hybrid models to break the curse
of dimensionality},
journal = {PLOS ONE},
volume = {17},
number = {9},
issn = {1932-6203},
address = {San Francisco, California, US},
publisher = {PLOS},
reportid = {FZJ-2022-03403},
pages = {e0274569 -},
year = {2022},
abstract = {Mechanistic/data-driven hybrid modeling is a key approach
when the mechanistic details of the processes at hand are
not sufficiently well understood, but also inferring a model
purely from data is too complex. By the integration of first
principles into a data-driven approach, hybrid modeling
promises a feasible data demand alongside extrapolation. In
this work, we introduce a learning strategy for
tree-structured hybrid models to perform a binary
classification task. Given a set of binary labeled data, the
challenge is to use them to develop a model that accurately
assesses labels of new unlabeled data. Our strategy employs
graph-theoretic methods to analyze the data and deduce a
function that maps input features to output labels. Our
focus here is on data sets represented by binary features in
which the label assessment of unlabeled data points is
always extrapolation. Our strategy shows the existence of
small sets of data points within given binary data for which
knowing the labels allows for extrapolation to the entire
valid input space. An implementation of our strategy yields
a notable reduction of training-data demand in a binary
classification task compared with different supervised
machine learning algorithms. As an application, we have
fitted a tree-structured hybrid model to the vital status of
a cohort of COVID-19 patients requiring intensive-care unit
treatment and mechanical ventilation. Our learning strategy
yields the existence of patient cohorts for whom knowing the
vital status enables extrapolation to the entire valid input
space of the developed hybrid model.},
cin = {JSC},
ddc = {610},
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 = {36107916},
UT = {WOS:000892087100079},
doi = {10.1371/journal.pone.0274569},
url = {https://juser.fz-juelich.de/record/909773},
}