Comparing poor and favorable outcome prediction with machine learning after mechanical thrombectomy in acute ischemic stroke

Background and PurposeOutcome prediction after mechanical thrombectomy (MT) in patients with acute ischemic stroke (AIS) and large vessel occlusion (LVO) is commonly performed by focusing on favorable outcome (modified Rankin Scale, mRS 0-2) after 3 months but poor outcome representing severe disabi...

Full description

Saved in:
Bibliographic Details
Main Authors: Mutke, Matthias Anthony (Author) , Madai, Vince Istvan (Author) , Hilbert, Adam (Author) , Zihni, Esra (Author) , Potreck, Arne (Author) , Weyland, Charlotte S. (Author) , Möhlenbruch, Markus Alfred (Author) , Heiland, Sabine (Author) , Ringleb, Peter A. (Author) , Nagel, Simon (Author) , Bendszus, Martin (Author) , Frey, Dietmar (Author)
Format: Article (Journal)
Language:English
Published: 27 May 2022
In: Frontiers in neurology
Year: 2022, Volume: 13, Pages: 1-11
ISSN:1664-2295
Online Access:Verlag, kostenfrei, Volltext: https://www.frontiersin.org/articles/10.3389/fneur.2022.737667
Get full text
Author Notes:Matthias A. Mutke, Vince I. Madai, Adam Hilbert, Esra Zihni, Arne Potreck, Charlotte S. Weyland, Markus A. Möhlenbruch, Sabine Heiland, Peter A. Ringleb, Simon Nagel, Martin Bendszus and Dietmar Frey

MARC

LEADER 00000caa a2200000 c 4500
001 1809305136
003 DE-627
005 20220927110434.0
007 cr uuu---uuuuu
008 220706s2022 xx |||||o 00| ||eng c
024 7 |a 10.3389/fneur.2022.737667  |2 doi 
035 |a (DE-627)1809305136 
035 |a (DE-599)KXP1809305136 
035 |a (OCoLC)1341463506 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Mutke, Matthias Anthony  |d 1987-  |e VerfasserIn  |0 (DE-588)1126261769  |0 (DE-627)88085622X  |0 (DE-576)484425633  |4 aut 
245 1 0 |a Comparing poor and favorable outcome prediction with machine learning after mechanical thrombectomy in acute ischemic stroke  |c Matthias A. Mutke, Vince I. Madai, Adam Hilbert, Esra Zihni, Arne Potreck, Charlotte S. Weyland, Markus A. Möhlenbruch, Sabine Heiland, Peter A. Ringleb, Simon Nagel, Martin Bendszus and Dietmar Frey 
264 1 |c 27 May 2022 
300 |a 11 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 06.07.2022 
520 |a Background and PurposeOutcome prediction after mechanical thrombectomy (MT) in patients with acute ischemic stroke (AIS) and large vessel occlusion (LVO) is commonly performed by focusing on favorable outcome (modified Rankin Scale, mRS 0-2) after 3 months but poor outcome representing severe disability and mortality (mRS 5 and 6) might be of equal importance for clinical decision-making.MethodsWe retrospectively analyzed patients with AIS and LVO undergoing MT from 2009 to 2018. Prognostic variables were grouped in baseline clinical (A), MRI-derived variables including mismatch [apparent diffusion coefficient (ADC) and time-to-maximum (Tmax) lesion volume] (B), and variables reflecting speed and extent of reperfusion (C) [modified treatment in cerebral ischemia (mTICI) score and time from onset to mTICI]. Three different scenarios were analyzed: (1) baseline clinical parameters only, (2) baseline clinical and MRI-derived parameters, and (3) all baseline clinical, imaging-derived, and reperfusion-associated parameters. For each scenario, we assessed prediction for favorable and poor outcome with seven different machine learning algorithms.ResultsIn 210 patients, prediction of favorable outcome was improved after including speed and extent of recanalization [highest area under the curve (AUC) 0.73] compared to using baseline clinical variables only (highest AUC 0.67). Prediction of poor outcome remained stable by using baseline clinical variables only (highest AUC 0.71) and did not improve further by additional variables. Prediction of favorable and poor outcomes was not improved by adding MR-mismatch variables. Most important baseline clinical variables for both outcomes were age, National Institutes of Health Stroke Scale, and premorbid mRS.ConclusionsOur results suggest that a prediction of poor outcome after AIS and MT could be made based on clinical baseline variables only. Speed and extent of MT did improve prediction for a favorable outcome but is not relevant for poor outcome. An MR mismatch with small ischemic core and larger penumbral tissue showed no predictive importance. 
700 1 |a Madai, Vince Istvan  |e VerfasserIn  |0 (DE-588)115165972X  |0 (DE-627)1012141020  |0 (DE-576)497995646  |4 aut 
700 1 |a Hilbert, Adam  |e VerfasserIn  |4 aut 
700 1 |a Zihni, Esra  |e VerfasserIn  |4 aut 
700 1 |a Potreck, Arne  |e VerfasserIn  |0 (DE-588)1031679790  |0 (DE-627)737108886  |0 (DE-576)379370638  |4 aut 
700 1 |a Weyland, Charlotte S.  |d 1990-  |e VerfasserIn  |0 (DE-588)1208458426  |0 (DE-627)1694725235  |4 aut 
700 1 |a Möhlenbruch, Markus Alfred  |d 1979-  |e VerfasserIn  |0 (DE-588)137693591  |0 (DE-627)594845041  |0 (DE-576)304845655  |4 aut 
700 1 |a Heiland, Sabine  |e VerfasserIn  |0 (DE-588)106732626X  |0 (DE-627)818624450  |0 (DE-576)426561368  |4 aut 
700 1 |a Ringleb, Peter A.  |e VerfasserIn  |0 (DE-588)1032676175  |0 (DE-627)73863364X  |0 (DE-576)172917743  |4 aut 
700 1 |a Nagel, Simon  |d 1974-  |e VerfasserIn  |0 (DE-588)129036072  |0 (DE-627)38788775X  |0 (DE-576)297460218  |4 aut 
700 1 |a Bendszus, Martin  |e VerfasserIn  |0 (DE-588)1032676426  |0 (DE-627)738634131  |0 (DE-576)175567697  |4 aut 
700 1 |a Frey, Dietmar  |e VerfasserIn  |0 (DE-588)1237243920  |0 (DE-627)1763184404  |4 aut 
773 0 8 |i Enthalten in  |t Frontiers in neurology  |d Lausanne : Frontiers Research Foundation, 2008  |g 13(2022), Artikel-ID 737667, Seite 1-11  |h Online-Ressource  |w (DE-627)631498753  |w (DE-600)2564214-5  |w (DE-576)326550933  |x 1664-2295  |7 nnas  |a Comparing poor and favorable outcome prediction with machine learning after mechanical thrombectomy in acute ischemic stroke 
773 1 8 |g volume:13  |g year:2022  |g elocationid:737667  |g pages:1-11  |g extent:11  |a Comparing poor and favorable outcome prediction with machine learning after mechanical thrombectomy in acute ischemic stroke 
856 4 0 |u https://www.frontiersin.org/articles/10.3389/fneur.2022.737667  |x Verlag  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20220706 
993 |a Article 
994 |a 2022 
998 |g 1032676426  |a Bendszus, Martin  |m 1032676426:Bendszus, Martin  |d 910000  |d 911100  |d 50000  |e 910000PB1032676426  |e 911100PB1032676426  |e 50000PB1032676426  |k 0/910000/  |k 1/910000/911100/  |k 0/50000/  |p 11 
998 |g 129036072  |a Nagel, Simon  |m 129036072:Nagel, Simon  |d 910000  |d 911100  |d 50000  |e 910000PN129036072  |e 911100PN129036072  |e 50000PN129036072  |k 0/910000/  |k 1/910000/911100/  |k 0/50000/  |p 10 
998 |g 1032676175  |a Ringleb, Peter A.  |m 1032676175:Ringleb, Peter A.  |d 910000  |d 911100  |e 910000PR1032676175  |e 911100PR1032676175  |k 0/910000/  |k 1/910000/911100/  |p 9 
998 |g 106732626X  |a Heiland, Sabine  |m 106732626X:Heiland, Sabine  |d 910000  |d 911100  |d 50000  |e 910000PH106732626X  |e 911100PH106732626X  |e 50000PH106732626X  |k 0/910000/  |k 1/910000/911100/  |k 0/50000/  |p 8 
998 |g 137693591  |a Möhlenbruch, Markus Alfred  |m 137693591:Möhlenbruch, Markus Alfred  |d 910000  |d 911100  |d 50000  |e 910000PM137693591  |e 911100PM137693591  |e 50000PM137693591  |k 0/910000/  |k 1/910000/911100/  |k 0/50000/  |p 7 
998 |g 1208458426  |a Weyland, Charlotte S.  |m 1208458426:Weyland, Charlotte S.  |d 910000  |d 911100  |d 50000  |e 910000PW1208458426  |e 911100PW1208458426  |e 50000PW1208458426  |k 0/910000/  |k 1/910000/911100/  |k 0/50000/  |p 6 
998 |g 1031679790  |a Potreck, Arne  |m 1031679790:Potreck, Arne  |d 910000  |d 911400  |e 910000PP1031679790  |e 911400PP1031679790  |k 0/910000/  |k 1/910000/911400/  |p 5 
998 |g 1126261769  |a Mutke, Matthias Anthony  |m 1126261769:Mutke, Matthias Anthony  |d 910000  |d 911100  |e 910000PM1126261769  |e 911100PM1126261769  |k 0/910000/  |k 1/910000/911100/  |p 1  |x j 
999 |a KXP-PPN1809305136  |e 416188494X 
BIB |a Y 
SER |a journal 
JSO |a {"note":["Gesehen am 06.07.2022"],"relHost":[{"pubHistory":["2008 -"],"title":[{"title_sort":"Frontiers in neurology","title":"Frontiers in neurology"}],"part":{"text":"13(2022), Artikel-ID 737667, Seite 1-11","year":"2022","volume":"13","pages":"1-11","extent":"11"},"language":["eng"],"disp":"Comparing poor and favorable outcome prediction with machine learning after mechanical thrombectomy in acute ischemic strokeFrontiers in neurology","physDesc":[{"extent":"Online-Ressource"}],"id":{"issn":["1664-2295"],"zdb":["2564214-5"],"eki":["631498753"]},"note":["Gesehen am 18.08.20","Specialty sections: Autonomic Neuroscience; Brain Imaging Methods; Dementia; Endovascular and Interventional Neurology; Epilepsy; Headache Medicine and Facial Pain; Movement Disorders; Multiple Sclerosis and Neuroimmunology; Neurocritical and Neurohospitalist; Care; Neurodegeneration; Neurogenomics; Neurology Education; Neuromuscular Diseases; Neuro-Oncology; Neuro-Ophthalmology; Neuro-Otology; Neuropediatrics; Neuropharmacology; Neuroprosthetics; Neurotrauma; Sleep and Chronobiology; Spinal Cord Medicine; Sports Neurology; Stroke; Teleneurology"],"origin":[{"publisherPlace":"Lausanne","dateIssuedDisp":"2008-","publisher":"Frontiers Research Foundation","dateIssuedKey":"2008"}],"recId":"631498753","titleAlt":[{"title":"Autonomic Neuroscience"},{"title":"Brain Imaging Methods"},{"title":"Dementia"},{"title":"Endovascular and Interventional Neurology"},{"title":"Epilepsy"},{"title":"Headache Medicine and Facial Pain"},{"title":"Movement Disorders"},{"title":"Multiple Sclerosis and Neuroimmunology"},{"title":"Neurocritical and Neurohospitalist Care"},{"title":"Neurodegeneration"},{"title":"Neurogenomics"},{"title":"Neurology Education"},{"title":"Neuromuscular Diseases"},{"title":"Neuro-Oncology"},{"title":"Neuro-Ophthalmology"},{"title":"Neuro-Otology"},{"title":"Neuropediatrics"},{"title":"Neuropharmacology"},{"title":"Neuroprosthetics"},{"title":"Neurotrauma"},{"title":"Sleep and Chronobiology"},{"title":"Spinal Cord Medicine"},{"title":"Sports Neurology"},{"title":"Stroke"},{"title":"Teleneurology"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"name":{"displayForm":["Frontiers Research Foundation"]}}],"id":{"doi":["10.3389/fneur.2022.737667"],"eki":["1809305136"]},"physDesc":[{"extent":"11 S."}],"recId":"1809305136","origin":[{"dateIssuedKey":"2022","dateIssuedDisp":"27 May 2022"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"person":[{"family":"Mutke","role":"aut","given":"Matthias Anthony","display":"Mutke, Matthias Anthony"},{"family":"Madai","given":"Vince Istvan","role":"aut","display":"Madai, Vince Istvan"},{"family":"Hilbert","display":"Hilbert, Adam","given":"Adam","role":"aut"},{"family":"Zihni","display":"Zihni, Esra","role":"aut","given":"Esra"},{"family":"Potreck","given":"Arne","role":"aut","display":"Potreck, Arne"},{"given":"Charlotte S.","role":"aut","display":"Weyland, Charlotte S.","family":"Weyland"},{"family":"Möhlenbruch","display":"Möhlenbruch, Markus Alfred","role":"aut","given":"Markus Alfred"},{"given":"Sabine","role":"aut","display":"Heiland, Sabine","family":"Heiland"},{"display":"Ringleb, Peter A.","given":"Peter A.","role":"aut","family":"Ringleb"},{"family":"Nagel","display":"Nagel, Simon","role":"aut","given":"Simon"},{"role":"aut","given":"Martin","display":"Bendszus, Martin","family":"Bendszus"},{"family":"Frey","display":"Frey, Dietmar","given":"Dietmar","role":"aut"}],"name":{"displayForm":["Matthias A. Mutke, Vince I. Madai, Adam Hilbert, Esra Zihni, Arne Potreck, Charlotte S. Weyland, Markus A. Möhlenbruch, Sabine Heiland, Peter A. Ringleb, Simon Nagel, Martin Bendszus and Dietmar Frey"]},"language":["eng"],"title":[{"title":"Comparing poor and favorable outcome prediction with machine learning after mechanical thrombectomy in acute ischemic stroke","title_sort":"Comparing poor and favorable outcome prediction with machine learning after mechanical thrombectomy in acute ischemic stroke"}]} 
SRT |a MUTKEMATTHCOMPARINGP2720