Journal Article

DZNE-2024-01290

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Machine learning models for outcome prediction in thrombectomy for large anterior vessel occlusion.

Shirvani Samani, O. (First author)DZNE* ; Warnat-Herresthal, S.DZNE* ; Savchuk, I.DZNE* ; Bode, F.Extern* ; Nitsch, L. ; Stösser, S. ; Ebrahimi, T.Extern* ; von Danwitz, N.Extern* ; Asperger, H.Extern* ; Layer, J. ; Meissner, J. ; Thielscher, C.Extern* ; Dorn, F. ; Lehnen, N. ; Schultze, J. L.DZNE* ; Petzold, G. C.DZNE* ; Weller, J. M. ; Investigators, G.-E. (Collaboration Author) ; Alegiani, A. (Contributor) ; Berrouschot, J. (Contributor) ; Boeck-Behrens, T. (Contributor) ; Bohner, G. (Contributor) ; Borggrefe, J. (Contributor) ; Bormann, A. (Contributor) ; Braun, M. (Contributor) ; Dorn, F. (Contributor) ; Eckert, B. (Contributor) ; Ernemann, U. (Contributor) ; Ernst, M. (Contributor) ; Fiehler, J. (Contributor) ; Gröschel, K. (Contributor) ; Hattingen, J. (Contributor) ; Hamann, G. (Contributor) ; Heitkamp, C. (Contributor) ; Henn, K.-H. (Contributor) ; Keil, F. (Contributor) ; Kellert, L. (Contributor)Extern* ; Leischner, H. (Contributor) ; Ludolph, A. (Contributor) ; Maier, I. (Contributor) ; Nikoubashman, O. (Contributor) ; Nolte, C. (Contributor) ; Petersen, M. (Contributor) ; Poli, S. (Contributor) ; Petzold, G. C. (Contributor)Extern* ; Reich, A. (Contributor) ; Röther, J. (Contributor) ; Riedel, C. (Contributor) ; Schäfer, J. H. (Contributor) ; Schell, M. (Contributor) ; Schellinger, P. (Contributor) ; Siebert, E. (Contributor) ; Stögbauer, F. (Contributor) ; Thomalla, G. (Contributor) ; Tiedt, S. (Contributor) ; Trumm, C. (Contributor) ; Uphaus, T. (Contributor) ; Wunderlich, S. (Contributor)

2024
Wiley Chichester [u.a.]

This record in other databases:    

Please use a persistent id in citations: doi:10.1002/acn3.52185

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.

Keyword(s): 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)

---

Contributing Institute(s):

1. Vascular Neurology (AG Petzold)
2. Patient Studies (Bonn) (Patient Studies (Bonn))
3. Clinical Single Cell Omics (CSCO) / Systems Medicine (AG Schultze)

Research Program(s):

1. 353 - Clinical and Health Care Research (POF4-353) (POF4-353)
2. 354 - Disease Prevention and Healthy Aging (POF4-354) (POF4-354)

Appears in the scientific report 2024

---

Database coverage:
; ; ; ; Article Processing Charges ; Clarivate Analytics Master Journal List ; DOAJ Seal ; Ebsco Academic Search ; Essential Science Indicators ; Fees ; IF >= 5 ; JCR ; PubMed Central ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---