% 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{ShirvaniSamani:272873,
      author       = {Shirvani Samani, Omid and Warnat-Herresthal, Stefanie and
                      Savchuk, Ivan and Bode, Felix and Nitsch, Louisa and
                      Stösser, Sebastian and Ebrahimi, Taraneh and von Danwitz,
                      Niklas and Asperger, Hannah and Layer, Julia and Meissner,
                      Julius and Thielscher, Christian and Dorn, Franziska and
                      Lehnen, Nils and Schultze, Joachim L and Petzold, Gabor C
                      and Weller, Johannes M},
      collaboration = {Investigators, GSR-ET},
      othercontributors = {Alegiani, Anna and Berrouschot, Jörg and Boeck-Behrens,
                          Tobias and Bohner, Georg and Borggrefe, Jan and Bormann,
                          Albrecht and Braun, Michael and Dorn, Franziska and Eckert,
                          Bernd and Ernemann, Ulrike and Ernst, Marielle and Fiehler,
                          Jens and Gröschel, Klaus and Hattingen, Jörg and Hamann,
                          Gerhard and Heitkamp, Christian and Henn, Karl-Heinz and
                          Keil, Fee and Kellert, Lars and Leischner, Hannes and
                          Ludolph, Alexander and Maier, Ilko and Nikoubashman, Omid
                          and Nolte, Christian and Petersen, Martina and Poli, Sven
                          and Petzold, Gabor C and Reich, Arno and Röther, Joachim
                          and Riedel, Christian and Schäfer, Jan Hendrik and Schell,
                          Maximilian and Schellinger, Peter and Siebert, Eberhard and
                          Stögbauer, Florian and Thomalla, Götz and Tiedt, Steffen
                          and Trumm, Christoph and Uphaus, Timo and Wunderlich, Silke},
      title        = {{M}achine learning models for outcome prediction in
                      thrombectomy for large anterior vessel occlusion.},
      journal      = {Annals of Clinical and Translational Neurology},
      volume       = {11},
      number       = {10},
      issn         = {2328-9503},
      address      = {Chichester [u.a.]},
      publisher    = {Wiley},
      reportid     = {DZNE-2024-01290},
      pages        = {2696 - 2706},
      year         = {2024},
      abstract     = {Predicting long-term functional outcomes shortly after a
                      stroke is challenging, even for experienced neurologists.
                      Therefore, we aimed to evaluate multiple machine learning
                      models and the importance of clinical/radiological
                      parameters to develop a model that balances minimal input
                      data with reliable predictions of long-term functional
                      independency.Our study utilized data from the German Stroke
                      Registry on patients with large anterior vessel occlusion
                      who underwent endovascular treatment. We trained seven
                      machine learning models using 30 parameters from the first
                      day postadmission to predict a modified Ranking Scale of 0-2
                      at 90 days poststroke. Model performance was assessed using
                      a 20-fold cross-validation and one-sided Wilcoxon rank-sum
                      tests. Key features were identified through backward feature
                      selection.We included 7485 individuals with a median age of
                      75 years and a median NIHSS score at admission of 14 in our
                      analysis. Our Deep Neural Network model demonstrated the
                      best performance among all models including data from 24 h
                      postadmission. Backward feature selection identified the
                      seven most important features to be NIHSS after 24 h, age,
                      modified Ranking Scale after 24 h, premorbid modified
                      Ranking Scale, intracranial hemorrhage within 24 h,
                      intravenous thrombolysis, and NIHSS at admission. Narrowing
                      the Deep Neural Network model's input data to these features
                      preserved the high performance with an AUC of 0.9 (CI:
                      0.89-0.91).Our Deep Neural Network model, trained on over
                      7000 patients, predicts 90-day functional independence using
                      only seven clinical/radiological features from the first day
                      postadmission, demonstrating both high accuracy and
                      practicality for clinical implementation on stroke units.},
      keywords     = {Humans / Aged / Male / Female / Machine Learning /
                      Thrombectomy: methods / Middle Aged / Aged, 80 and over /
                      Registries / Endovascular Procedures: methods / Ischemic
                      Stroke: surgery / Outcome Assessment, Health Care /
                      Prognosis / Stroke},
      cin          = {AG Petzold / Patient Studies (Bonn) / AG Schultze},
      ddc          = {610},
      cid          = {I:(DE-2719)1013020 / I:(DE-2719)1011101 /
                      I:(DE-2719)1013038},
      pnm          = {353 - Clinical and Health Care Research (POF4-353) / 354 -
                      Disease Prevention and Healthy Aging (POF4-354)},
      pid          = {G:(DE-HGF)POF4-353 / G:(DE-HGF)POF4-354},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:39180278},
      pmc          = {pmc:PMC11514938},
      doi          = {10.1002/acn3.52185},
      url          = {https://pub.dzne.de/record/272873},
}