Journal article
Machine Learning–Based Identification of Target Groups for Thrombectomy in Acute Stroke
- Abstract:
- Background and purposeStroke is a leading cause of morbidity and mortality worldwide. Endovascular therapy (EVT) has been established as a gold standard option to treat acute ischemic stroke (AIS) patients with large vessel occlusion (LVO) presenting within 6 h of symptom onset. However, there is a paucity of information regarding patient outcome and mortality in patients presenting in late time window within 6 to 24 h. In this study, we aimed to assess for predictors of outcomes in late window stroke patients following EVT.MethodsWe analyzed data from 202 patients treated with EVT from four comprehensive stroke centers. All patients were above 18 years of age and had symptoms onset of 6–24 h. mRS of 0–2 after three months was defined as favorable outcome.ResultsPatients with favorable outcome had lower median age (p = 0.003), lower pre-EVT National Institute of Health Stroke Scale (NIHSS) score (p = 0.000), lower diabetes mellitus (p = 0.041), stroke history (p = 0.041), parenchymal hematoma (PH) (p = 0.000) and fewer attempts to achieve successful recanalization (p = 0.001). Multivariate regression analysis found age (p = 0.007), diabetes mellitus (p = 0.022), successful recanalization (mTICI≥2b) (p = 0.006), NIHSS at onset (p = 0.000), and PH1 + PH2 Heidelberg bleeding classification (p = 0.009) as predictors of functional outcome.ConclusionAge, diabetes mellitus history, baseline NIHSS score, successful recanalization, and PH are predictors of 90-day functional outcome of late-window ischemic stroke patients undergoing EVT
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Version of record, pdf, 962.9KB, Terms of use)
-
- Publisher copy:
- 10.1007/s12975-022-01040-5
Authors
- Publisher:
- Springer
- Journal:
- Translational Stroke Research More from this journal
- Volume:
- 14
- Issue:
- 3
- Pages:
- 311-321
- Publication date:
- 2022-06-07
- DOI:
- EISSN:
-
1868-601X
- ISSN:
-
1868-4483
- Language:
-
English
- Keywords:
- Pubs id:
-
1269627
- Local pid:
-
pubs:1269627
- Source identifiers:
-
W4281844823
- Deposit date:
-
2026-04-27
- ARK identifier:
This ORA record was generated from metadata provided by an external service. It has not been edited by the ORA Team.
Terms of use
- Copyright date:
- 2022
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record