Advertisement

Development and validation of comprehensive clinical outcome prediction models for acute ischaemic stroke in anterior circulation based on machine learning

  • Author Footnotes
    1 These authors contributed equally to this work and are co-first authors.
    Haiyan Zhang
    Footnotes
    1 These authors contributed equally to this work and are co-first authors.
    Affiliations
    Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China
    Search for articles by this author
  • Author Footnotes
    1 These authors contributed equally to this work and are co-first authors.
    Hongyi Chen
    Footnotes
    1 These authors contributed equally to this work and are co-first authors.
    Affiliations
    Academy for Engineering and Technology, Fudan University, Shanghai, China
    Search for articles by this author
  • Chao Zhang
    Affiliations
    Department of Radiology, Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China
    Search for articles by this author
  • Aihong Cao
    Affiliations
    Department of Radiology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China
    Search for articles by this author
  • Zekuan Yu
    Affiliations
    Academy for Engineering and Technology, Fudan University, Shanghai, China
    Search for articles by this author
  • Hao Wu
    Correspondence
    Corresponding authors at: Huashan Hospital, Fudan University, 12 Wulumuqi Middle Road, Shanghai 200040, China (H. Wu). Department of Radiology, Huashan Hospital, Fudan University, 12 Wulumuqi Middle Road, Shanghai 200040, China (J. Zhang and D. Geng).
    Affiliations
    Huashan Hospital, Fudan University, Shanghai, China
    Search for articles by this author
  • Jun Zhang
    Correspondence
    Corresponding authors at: Huashan Hospital, Fudan University, 12 Wulumuqi Middle Road, Shanghai 200040, China (H. Wu). Department of Radiology, Huashan Hospital, Fudan University, 12 Wulumuqi Middle Road, Shanghai 200040, China (J. Zhang and D. Geng).
    Affiliations
    Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China

    Academy for Engineering and Technology, Fudan University, Shanghai, China
    Search for articles by this author
  • Daoying Geng
    Correspondence
    Corresponding authors at: Huashan Hospital, Fudan University, 12 Wulumuqi Middle Road, Shanghai 200040, China (H. Wu). Department of Radiology, Huashan Hospital, Fudan University, 12 Wulumuqi Middle Road, Shanghai 200040, China (J. Zhang and D. Geng).
    Affiliations
    Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China

    Academy for Engineering and Technology, Fudan University, Shanghai, China
    Search for articles by this author
  • Author Footnotes
    1 These authors contributed equally to this work and are co-first authors.

      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 access
      One-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 Neuroscience
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Furlanis G.
        • Ajčević M.
        • Stragapede L.
        • Lugnan C.
        • Ridolfi M.
        • Caruso P.
        • et al.
        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
        • Lange M.C.
        • Ribas G.
        • Scavasine V.
        • Ducci R.-P.
        • Mendes D.C.
        • Zétola V.d.H.F.
        • et al.
        Stroke recurrence in the different subtypes of ischemic stroke. The importance of the intracranial disease.
        Arq Neuro-Psiquiatr. 2018; 76: 649-653
        • Feigin V.
        • Nguyen G.
        • Cercy K.
        • Johnson C.
        • Alam T.
        • Parmar P.
        • et al.
        Global, regional, and country-specific lifetime risks of stroke, 1990 and 2016.
        N Engl J Med. 2018; 379: 2429-2437
        • Saposnik G.
        • iScore Research Team
        An integer-based score to predict functional outcome in acute ischemic stroke: the ASTRAL score.
        Neurology. 2012; 79 (author reply 93–4): 2293
        • Meseguer E.
        • Mazighi M.
        • Lapergue B.
        • Labreuche J.
        • Sirimarco G.
        • Gonzalez-Valcarcel J.
        • et al.
        Outcomes after thrombolysis in AIS according to prior statin use: a registry and review.
        Neurology. 2012; 79: 1817-1823
        • Strbian D.
        • Meretoja A.
        • Ahlhelm F.J.
        • Pitkaniemi J.
        • Lyrer P.
        • Kaste M.
        • et al.
        Predicting outcome of IV thrombolysis-treated ischemic stroke patients: the DRAGON score.
        Neurology. 2012; 78: 427-432
        • Saposnik G.
        • Raptis S.
        • Kapral M.K.
        • Liu Y.
        • Tu J.V.
        • Mamdani M.
        • et al.
        The iScore predicts poor functional outcomes early after hospitalization for an acute ischemic stroke.
        Stroke. 2011; 42: 3421-3428
        • Sarraj A.
        • Albright K.
        • Barreto A.D.
        • Boehme A.K.
        • Sitton C.W.
        • Choi J.
        • et al.
        Optimizing prediction scores for poor outcome after intra-arterial therapy in anterior circulation acute ischemic stroke.
        Stroke. 2013; 44: 3324-3330
        • Liggins J.
        • Yoo A.
        • Mishra N.
        • Wheeler H.
        • Straka M.
        • Leslie-Mazwi T.
        • et al.
        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
        • Ryu C.-W.
        • Kim B.M.
        • Kim H.-G.
        • Heo J.H.
        • Nam H.S.
        • Kim D.J.
        • et al.
        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
        • Seo W.-K.
        • Liebeskind D.S.
        • Yoo B.
        • Sharma L.
        • Jahan R.
        • Duckwiler G.
        • et al.
        Predictors and functional outcomes of fast, intermediate, and slow progression among patients with acute ischemic stroke.
        Stroke. 2020; 51: 2553-2557
        • Wang Z.
        • Xie J.
        • Tang T.-Y.
        • Zeng C.-H.
        • Zhang Y.i.
        • Zhao Z.
        • et al.
        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
        • Xie Y.u.
        • Oppenheim C.
        • Guillemin F.
        • Gautheron V.
        • Gory B.
        • Raoult H.
        • et al.
        Pretreatment lesional volume impacts clinical outcome and thrombectomy efficacy.
        Ann Neurol. 2018; 83: 178-185
        • Lee J.
        • Lee S.
        • Yoo J.
        • Hong J.
        • Kim C.
        • Kim Y.
        • et al.
        Prognosis of acute intracranial atherosclerosis-related occlusion after endovascular treatment.
        J Stroke. 2018; 20: 394-403
        • Saver J.L.
        • Goyal M.
        • van der Lugt A.
        • Menon B.K.
        • Majoie C.B.L.M.
        • Dippel D.W.
        • et al.
        Time to treatment with endovascular thrombectomy and outcomes from ischemic stroke: a meta-analysis.
        JAMA. 2016; 316: 1279
        • D'Ascenzo F.
        • De Filippo O.
        • Gallone G.
        • Mittone G.
        • Deriu M.A.
        • Iannaccone M.
        • et al.
        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
        • Chen S.
        • Jiang L.
        • Zhang E.
        • Hu S.
        • Wang T.
        • Gao F.
        • et al.
        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
        • Lin L.
        • Bivard A.
        • Kleinig T.
        • Spratt N.J.
        • Levi C.R.
        • Yang Q.
        • et al.
        Correction for delay and dispersion results in more accurate cerebral blood flow ischemic core measurement in acute stroke.
        Stroke. 2018; 49: 924-930
        • Tian H.
        • Parsons M.W.
        • Levi C.R.
        • Lin L.
        • Aviv R.I.
        • Spratt N.J.
        • et al.
        Influence of occlusion site and baseline ischemic core on outcome in patients with ischemic stroke.
        Neurology. 2019; 92: e2626-e2643
        • Lin L.
        • Bivard A.
        • Krishnamurthy V.
        • Levi C.
        • Parsons M.
        Whole-brain CT perfusion to quantify acute ischemic penumbra and core.
        Radiology. 2016; 279: 876-887
        • Lin L.
        • Chen C.
        • Tian H.
        • Bivard A.
        • Spratt N.
        • Levi C.R.
        • et al.
        Perfusion computed tomography accurately quantifies collateral flow after acute ischemic stroke.
        Stroke. 2020; 51: 1006-1009
        • Wheeler H.M.
        • Mlynash M.
        • Inoue M.
        • Tipirnini A.
        • Liggins J.
        • Bammer R.
        • et al.
        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
      1. 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.

        • Iizuka T.
        • Kaneko J.
        • Tominaga N.
        • Someko H.
        • Nakamura M.
        • Ishima D.
        • et al.
        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
      2. 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.

        • Xu Z.
        • Kurek A.
        • Cannon S.
        • Beavis W.
        Predictions from algorithmic modeling result in better decisions than from data modeling for soybean iron deficiency chlorosis.
        PLoS ONE. 2021; 16: e0240948
        • Liu Q.
        • Jiang P.
        • Jiang Y.
        • Ge H.
        • Li S.
        • Jin H.
        • et al.
        Development and validation of an institutional nomogram for aiding aneurysm rupture risk stratification.
        Sci Rep. 2021; 11
        • Zhou T.
        • Chen L.
        • Guo J.
        • Zhang M.
        • Zhang Y.
        • Cao S.
        • et al.
        MSIFinder: a python package for detecting MSI status using random forest classifier.
        BMC Bioinform. 2021; 22
        • Altmann A.
        • Toloşi L.
        • Sander O.
        • Lengauer T.
        Permutation importance: a corrected feature importance measure.
        Bioinform (Oxf Engl). 2010; 26: 1340-1347
        • Loeve M.
        • de Bruijne M.
        • Hartmann I.C.
        • van Straten M.
        • Hop W.C.
        • Tiddens H.A.
        Three-section expiratory CT: insufficient for trapped air assessment in patients with cystic fibrosis.
        Radiology. 2012; 262: 969-976
      3. 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.

        • Yang P.
        • Zhang Y.
        • Zhang L.
        • Zhang Y.
        • Treurniet K.M.
        • Chen W.
        • et al.
        Endovascular thrombectomy with or without intravenous alteplase in acute stroke.
        N Engl J Med. 2020; 382: 1981-1993
        • Ma H.
        • Campbell B.C.V.
        • Parsons M.W.
        • Churilov L.
        • Levi C.R.
        • Hsu C.
        • et al.
        Thrombolysis guided by perfusion imaging up to 9 hours after onset of stroke.
        N Engl J Med. 2019; 380: 1795-1803
      4. Lyden P. Measuring outcome after stroke: more lessons learned again. Stroke, 2020, 51(4): 1053-54.