272873 20241108164738.0 10.1002/acn3.52185 doi pmid:39180278 pmid pmc:PMC11514938 pmc DZNE-2024-01290 English 610 Shirvani Samani, Omid P:(DE-2719)9002936 0 First author dzne Machine learning models for outcome prediction in thrombectomy for large anterior vessel occlusion. Chichester [u.a.] 2024 Wiley article DRIVER Output Types/Journal article DataCite Journal Article journal journal PUB:(DE-HGF)16 1731077645_3251 PUB:(DE-HGF) ARTICLE BibTeX JOURNAL_ARTICLE ORCID Journal Article 0 EndNote 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. 353 - Clinical and Health Care Research (POF4-353) G:(DE-HGF)POF4-353 POF4-353 POF IV 0 354 - Disease Prevention and Healthy Aging (POF4-354) G:(DE-HGF)POF4-354 POF4-354 POF IV 1 Dataset connected to CrossRef, PubMed, , Journals: pub.dzne.de Humans MeSH Aged MeSH Male MeSH Female MeSH Machine Learning MeSH Thrombectomy: methods MeSH Middle Aged MeSH Aged, 80 and over MeSH Registries MeSH Endovascular Procedures: methods MeSH Ischemic Stroke: surgery MeSH Outcome Assessment, Health Care MeSH Prognosis MeSH Stroke MeSH Warnat-Herresthal, Stefanie P:(DE-2719)9001511 1 dzne Savchuk, Ivan P:(DE-2719)9002246 2 dzne Bode, Felix P:(DE-2719)2811949 3 dzne Nitsch, Louisa 4 Stösser, Sebastian 5 Ebrahimi, Taraneh P:(DE-2719)9003076 6 dzne von Danwitz, Niklas P:(DE-2719)9003408 7 dzne Asperger, Hannah P:(DE-2719)9003181 8 dzne Layer, Julia 9 Meissner, Julius 10 Thielscher, Christian P:(DE-2719)9002386 11 dzne Dorn, Franziska 12 Lehnen, Nils 13 Schultze, Joachim L P:(DE-2719)2811660 14 dzne Petzold, Gabor C P:(DE-2719)2810273 15 dzne Weller, Johannes M 16 Investigators, GSR-ET 17 Collaboration Author Alegiani, Anna 18 Contributor Berrouschot, Jörg 19 Contributor Boeck-Behrens, Tobias 20 Contributor Bohner, Georg 21 Contributor Borggrefe, Jan 22 Contributor Bormann, Albrecht 23 Contributor Braun, Michael 24 Contributor Dorn, Franziska 25 Contributor Eckert, Bernd 26 Contributor Ernemann, Ulrike 27 Contributor Ernst, Marielle 28 Contributor Fiehler, Jens 29 Contributor Gröschel, Klaus 30 Contributor Hattingen, Jörg 31 Contributor Hamann, Gerhard 32 Contributor Heitkamp, Christian 33 Contributor Henn, Karl-Heinz 34 Contributor Keil, Fee 35 Contributor Kellert, Lars P:(DE-2719)9003034 36 Contributor dzne Leischner, Hannes 37 Contributor Ludolph, Alexander 38 Contributor Maier, Ilko 39 Contributor Nikoubashman, Omid 40 Contributor Nolte, Christian P:(DE-2719)9000234 41 Contributor Petersen, Martina 42 Contributor Poli, Sven 43 Contributor Petzold, Gabor C P:(DE-2719)2810273 44 Contributor dzne Reich, Arno 45 Contributor Röther, Joachim 46 Contributor Riedel, Christian 47 Contributor Schäfer, Jan Hendrik 48 Contributor Schell, Maximilian 49 Contributor Schellinger, Peter 50 Contributor Siebert, Eberhard 51 Contributor Stögbauer, Florian 52 Contributor Thomalla, Götz 53 Contributor Tiedt, Steffen 54 Contributor Trumm, Christoph 55 Contributor Uphaus, Timo 56 Contributor Wunderlich, Silke 57 Contributor 10.1002/acn3.52185 Vol. 11, no. 10, p. 2696 - 2706 PERI:(DE-600)2740696-9 10 2696 - 2706 Annals of Clinical and Translational Neurology 11 2024 2328-9503 OpenAccess http://pub.dzne.de/record/272873/files/DZNE-2024-01290.pdf OpenAccess pdfa http://pub.dzne.de/record/272873/files/DZNE-2024-01290.pdf?subformat=pdfa oai:pub.dzne.de:272873 openaire open_access VDB driver dnbdelivery Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 0 P:(DE-2719)9002936 Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 1 P:(DE-2719)9001511 Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 2 P:(DE-2719)9002246 External Institute I:(DE-HGF)0 Extern 3 P:(DE-2719)2811949 External Institute I:(DE-HGF)0 Extern 6 P:(DE-2719)9003076 External Institute I:(DE-HGF)0 Extern 7 P:(DE-2719)9003408 External Institute I:(DE-HGF)0 Extern 8 P:(DE-2719)9003181 External Institute I:(DE-HGF)0 Extern 11 P:(DE-2719)9002386 Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 14 P:(DE-2719)2811660 Deutsches Zentrum für Neurodegenerative Erkrankungen I:(DE-588)1065079516 DZNE 15 P:(DE-2719)2810273 External Institute I:(DE-HGF)0 Extern 36 P:(DE-2719)9003034 External Institute I:(DE-HGF)0 Extern 44 P:(DE-2719)2810273 DE-HGF Gesundheit Neurodegenerative Diseases G:(DE-HGF)POF4-350 G:(DE-HGF)POF4-353 G:(DE-HGF)POF4 G:(DE-HGF)POF4-300 G:(DE-HGF)POF Clinical and Health Care Research 0 DE-HGF Gesundheit Neurodegenerative Diseases G:(DE-HGF)POF4-350 G:(DE-HGF)POF4-354 G:(DE-HGF)POF4 G:(DE-HGF)POF4-300 G:(DE-HGF)POF Disease Prevention and Healthy Aging 1 2024 DBCoverage StatID:(DE-HGF)0200 StatID SCOPUS 2023-08-22 DBCoverage StatID:(DE-HGF)0160 StatID Essential Science Indicators 2023-08-22 Creative Commons Attribution CC BY 4.0 LIC:(DE-HGF)CCBY4 HGFVOC DBCoverage StatID:(DE-HGF)0600 StatID Ebsco Academic Search 2023-08-22 JCR StatID:(DE-HGF)0100 StatID ANN CLIN TRANSL NEUR : 2022 2023-08-22 DBCoverage StatID:(DE-HGF)0501 StatID DOAJ Seal 2021-04-16T15:13:11Z DBCoverage StatID:(DE-HGF)0500 StatID DOAJ 2021-04-16T15:13:11Z WoS StatID:(DE-HGF)0113 StatID Science Citation Index Expanded 2023-08-22 Fees StatID:(DE-HGF)0700 StatID 2023-08-22 DBCoverage StatID:(DE-HGF)0150 StatID Web of Science Core Collection 2023-08-22 OpenAccess StatID:(DE-HGF)0510 StatID Peer Review StatID:(DE-HGF)0030 StatID ASC 2023-08-22 Article Processing Charges StatID:(DE-HGF)0561 StatID 2023-08-22 IF >= 5 StatID:(DE-HGF)9905 StatID ANN CLIN TRANSL NEUR : 2022 2023-08-22 DBCoverage StatID:(DE-HGF)0300 StatID Medline 2023-08-22 DBCoverage StatID:(DE-HGF)0320 StatID PubMed Central 2023-08-22 DBCoverage StatID:(DE-HGF)0199 StatID Clarivate Analytics Master Journal List 2023-08-22 I:(DE-2719)1013020 AG Petzold Vascular Neurology 0 I:(DE-2719)1011101 Patient Studies (Bonn) Patient Studies (Bonn) 1 I:(DE-2719)1013038 AG Schultze Clinical Single Cell Omics (CSCO) / Systems Medicine 2 journal VDB UNRESTRICTED I:(DE-2719)1013020 I:(DE-2719)1011101 I:(DE-2719)1013038 FullTexts