Highlights
- •Most of the CTP parameters were strongly correlated with the clinical outcome of AIS.
- •ML models showed good performance in the prediction of clinical outcome of AIS.
- •The ensemble model showed best performance in the prediction of the clinical outcome of AIS.
Abstract
The current prediction models for the clinical outcome of acute ischaemic stroke (AIS)
remain insufficient for individualized patient management strategies. We aimed to
investigate machine learning (ML) performance in the clinical outcome prediction of
AIS in anterior circulation and evaluate the clinical outcome by combining the quantitative
evaluation indicators of perfusion features and basic clinical information. Four ML
classifiers, support vector machine (SVM), naive Bayes (NB), logistic regression (LR),
and random forest (RF) were trained on a cohort of 389 adult patients (training cohort
[70 %]; external validation cohort [30 %]) from the Acute Stroke Center Registry of
Huashan Hospital. Model performance was compared by a range of learning metrics. Most
imaging parameters were strongly correlated with the outcome (range, 0.57 to 0.81),
and the correlation between relative cerebral blood flow (rCBF) < 30 % and clinical
outcome was the strongest (ρ = 0.81). As the reference parameters increased, the performance
of the four models was greatly improved [SVM (AUC: from 0.79 to 0.99, F1-score: from
0.61 to 0.90), RF (AUC: from 0.88 to 0.98, F1-score: from 0.71 to 0.96), LR (AUC:
from 0.80 to 0.97, F1-score: from 0.64 to 0.95), and NB (AUC: from 0.74 to 0.97, F1-score:
from 0.66 to 0.92)]. The ensemble classifier model with all parameters had the highest
F1-score (0.97). All the ML models, jointly considering the basic clinical information
and quantitative evaluation indicators of computed tomography perfusion (CTP), showed
good performance in the prediction of clinical outcome of AIS in anterior circulation.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Journal of Clinical NeuroscienceAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Ischemic volume and neurological deficit: Correlation of computed tomography perfusion with the national institutes of health stroke scale score in acute ischemic stroke.J Stroke Cerebrovasc Dis. 2018; 27: 2200-2207
- Stroke recurrence in the different subtypes of ischemic stroke. The importance of the intracranial disease.Arq Neuro-Psiquiatr. 2018; 76: 649-653
- Global, regional, and country-specific lifetime risks of stroke, 1990 and 2016.N Engl J Med. 2018; 379: 2429-2437
- An integer-based score to predict functional outcome in acute ischemic stroke: the ASTRAL score.Neurology. 2012; 79 (author reply 93–4): 2293
- Outcomes after thrombolysis in AIS according to prior statin use: a registry and review.Neurology. 2012; 79: 1817-1823
- Predicting outcome of IV thrombolysis-treated ischemic stroke patients: the DRAGON score.Neurology. 2012; 78: 427-432
- The iScore predicts poor functional outcomes early after hospitalization for an acute ischemic stroke.Stroke. 2011; 42: 3421-3428
- Optimizing prediction scores for poor outcome after intra-arterial therapy in anterior circulation acute ischemic stroke.Stroke. 2013; 44: 3324-3330
- A score based on age and DWI volume predicts poor outcome following endovascular treatment for acute ischemic stroke.Int J Stroke. 2015; 10: 705-709
- Optimizing outcome prediction scores in patients undergoing endovascular thrombectomy for large vessel occlusions using collateral grade on computed tomography angiography.Neurosurgery. 2019; 85: 350-358
- Predictors and functional outcomes of fast, intermediate, and slow progression among patients with acute ischemic stroke.Stroke. 2020; 51: 2553-2557
- Collateral status at single-phase and multiphase CT angiography versus CT perfusion for outcome prediction in anterior circulation acute ischemic stroke.Radiology. 2020; 296: 393-400
- Pretreatment lesional volume impacts clinical outcome and thrombectomy efficacy.Ann Neurol. 2018; 83: 178-185
- Prognosis of acute intracranial atherosclerosis-related occlusion after endovascular treatment.J Stroke. 2018; 20: 394-403
- Time to treatment with endovascular thrombectomy and outcomes from ischemic stroke: a meta-analysis.JAMA. 2016; 316: 1279
- Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets.Lancet (Lond Engl). 2021; 397: 199-207
- A novel nomogram based on machine learning-pathomics signature and neutrophil to lymphocyte ratio for survival prediction of bladder cancer patients.Front Oncol. 2021; 11703033
- Correction for delay and dispersion results in more accurate cerebral blood flow ischemic core measurement in acute stroke.Stroke. 2018; 49: 924-930
- Influence of occlusion site and baseline ischemic core on outcome in patients with ischemic stroke.Neurology. 2019; 92: e2626-e2643
- Whole-brain CT perfusion to quantify acute ischemic penumbra and core.Radiology. 2016; 279: 876-887
- Perfusion computed tomography accurately quantifies collateral flow after acute ischemic stroke.Stroke. 2020; 51: 1006-1009
- The growth rate of early DWI lesions is highly variable and associated with penumbral salvage and clinical outcomes following endovascular reperfusion.Int J Stroke. 2015; 10: 723-729
Lin L, Yang J, Chen C, Tian H, Bivard A, Spratt NJ, et al. Association of collateral status and ischemic core growth in patients with acute ischemic stroke. Neurology, 2021, 96(2): e161-e70.
- Association of progressive cerebellar atrophy with long-term outcome in patients with anti-N-methyl-d-aspartate receptor encephalitis.JAMA Neurol. 2016; 73: 706-713
Lan Q, Li Y, Robertson J, Jin R. Modeling of pre-transplantation liver viability with spatial-temporal smooth variable selection. Comput Methods Programs Biomed, 2021, 208: 106264.
- Predictions from algorithmic modeling result in better decisions than from data modeling for soybean iron deficiency chlorosis.PLoS ONE. 2021; 16: e0240948
- Development and validation of an institutional nomogram for aiding aneurysm rupture risk stratification.Sci Rep. 2021; 11
- MSIFinder: a python package for detecting MSI status using random forest classifier.BMC Bioinform. 2021; 22
- Permutation importance: a corrected feature importance measure.Bioinform (Oxf Engl). 2010; 26: 1340-1347
- Three-section expiratory CT: insufficient for trapped air assessment in patients with cystic fibrosis.Radiology. 2012; 262: 969-976
Consoli A, Andersson T, Holmberg A, Verganti L, Saletti A, Vallone S, et al. CT perfusion and angiographic assessment of pial collateral reperfusion in acute ischemic stroke: the CAPRI study. J Neurointerv Surg, 2016, 8(12): 1211-16. [30] Albers G, Marks M, Kemp S, Christensen S, Tsai J, Ortega-Gutierrez S, et al. Thrombectomy for Stroke at 6 to 16 Hours with Selection by Perfusion Imaging. N Engl J Med, 2018, 378(8): 708-18.
- Endovascular thrombectomy with or without intravenous alteplase in acute stroke.N Engl J Med. 2020; 382: 1981-1993
- Thrombolysis guided by perfusion imaging up to 9 hours after onset of stroke.N Engl J Med. 2019; 380: 1795-1803
Lyden P. Measuring outcome after stroke: more lessons learned again. Stroke, 2020, 51(4): 1053-54.
Article info
Publication history
Accepted:
July 26,
2022
Received:
December 12,
2021
Identification
Copyright
© 2022 Elsevier Ltd. All rights reserved.
