Header

UZH-Logo

Maintenance Infos

Machine learning based outcome prediction in stroke patients with MCA‐M1 occlusions and early thrombectomy


Hamann, Janne; Herzog, Lisa; Wehrli, Carina; Dobrocky, Tomas; Bink, Andrea; Piccirelli, Marco; Panos, Leonidas; Kaesmacher, Johannes; Fischer, Urs; Stippich, Christoph; Luft, Andreas R; Gralla, Jan; Arnold, Marcel; Wiest, Roland; Sick, Beate; Wegener, Susanne (2020). Machine learning based outcome prediction in stroke patients with MCA‐M1 occlusions and early thrombectomy. European Journal of Neurology:Epub ahead of print.

Abstract

Background

Clinical outcome varies substantially between individuals with large vessel occlusion (LVO) stroke. A small infarct core and large mismatch were found to be associated with good recovery. We investigated if those imaging variables improve individual prediction of functional outcome after early (< 6h) endovascular treatment (EVT) in LVO stroke.
Methods

We included 222 patients with acute ischemic stroke due to middle cerebral artery (MCA)‐M1 occlusion who received EVT. As predictors, we used clinical variables and region of interest (ROI) based magnetic resonance imaging (MRI) features. We developed different machine learning models and quantified their prediction performance by the area under the curve (AUC) of receiver operator characteristics (ROC) curves and the Brier score.
Results

Successful recanalization rate was 78%, with 54% patients having a favorable outcome (modified Rankin scale, mRS 0‐2). Small infarct core was associated with favorable functional outcome. Outcome prediction improved only slightly when imaging was added to patient variables. Age was the driving factor, with a sharp decrease of likelihood for favorable functional outcome beyond 78 years of age.
Conclusions

In patients with MCA‐M1 occlusion strokes referred to EVT within 6 hours of symptom onset, infarct core volume was associated with outcome. However, ROI based imaging parameters led to no significant improvement in outcome prediction on individual patient level when added to a set of clinical predictors. Our study is in concordance with the current practice, where mismatch imaging or collateral readouts are not recommended for excluding patients with MCA‐M1 occlusion for early EVT.

Abstract

Background

Clinical outcome varies substantially between individuals with large vessel occlusion (LVO) stroke. A small infarct core and large mismatch were found to be associated with good recovery. We investigated if those imaging variables improve individual prediction of functional outcome after early (< 6h) endovascular treatment (EVT) in LVO stroke.
Methods

We included 222 patients with acute ischemic stroke due to middle cerebral artery (MCA)‐M1 occlusion who received EVT. As predictors, we used clinical variables and region of interest (ROI) based magnetic resonance imaging (MRI) features. We developed different machine learning models and quantified their prediction performance by the area under the curve (AUC) of receiver operator characteristics (ROC) curves and the Brier score.
Results

Successful recanalization rate was 78%, with 54% patients having a favorable outcome (modified Rankin scale, mRS 0‐2). Small infarct core was associated with favorable functional outcome. Outcome prediction improved only slightly when imaging was added to patient variables. Age was the driving factor, with a sharp decrease of likelihood for favorable functional outcome beyond 78 years of age.
Conclusions

In patients with MCA‐M1 occlusion strokes referred to EVT within 6 hours of symptom onset, infarct core volume was associated with outcome. However, ROI based imaging parameters led to no significant improvement in outcome prediction on individual patient level when added to a set of clinical predictors. Our study is in concordance with the current practice, where mismatch imaging or collateral readouts are not recommended for excluding patients with MCA‐M1 occlusion for early EVT.

Statistics

Citations

Altmetrics

Downloads

0 downloads since deposited on 24 Nov 2020
0 downloads since 12 months

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Clinic for Neurology
04 Faculty of Medicine > University Hospital Zurich > Clinic for Neuroradiology
04 Faculty of Medicine > Neuroscience Center Zurich
Dewey Decimal Classification:570 Life sciences; biology
610 Medicine & health
Uncontrolled Keywords:Neurology, Clinical Neurology
Language:English
Date:21 November 2020
Deposited On:24 Nov 2020 08:49
Last Modified:09 Dec 2020 15:59
Publisher:Wiley-Blackwell Publishing, Inc.
ISSN:1351-5101
OA Status:Closed
Publisher DOI:https://doi.org/10.1111/ene.14651
PubMed ID:33220140

Download

Closed Access: Download allowed only for UZH members

Content: Accepted Version
Language: English
Filetype: PDF - Registered users only until 21 November 2021
Size: 26MB
View at publisher
Embargo till: 2021-11-21