Advertisement

Stroke mortality prediction using machine learning: systematic review

  • Lihi Schwartz
    Correspondence
    Corresponding author at: Derech Sheba 2, Ramat Gan, Israel, 5262000.
    Affiliations
    Sheba Medical Center, Tel Hashomer, Israel, and Ben-Gurion University of the Negev, Be'er Sheva, Israel
    Search for articles by this author
  • Roi Anteby
    Affiliations
    Department of Surgery and Transplantation B, Sheba Medical Center, Tel Hashomer, Israel, and Sackler Medical School, Tel Aviv University, Tel Aviv, Israel
    Search for articles by this author
  • Eyal Klang
    Affiliations
    Institute for Healthcare Delivery Science, Department of Population Health Science and Policy, Mount Sinai, New York, NY, United States of America

    Deep Vision Lab, The Chaim Sheba Medical Center, Ramat Gan, Israel.

    Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel, and Sackler Medical School, Tel Aviv University, Tel Aviv, Israel
    Search for articles by this author
  • Shelly Soffer
    Affiliations
    Deep Vision Lab, The Chaim Sheba Medical Center, Ramat Gan, Israel.

    Internal Medicine B, Assuta Medical Center, Ashdod, Israel, and Ben-Gurion University of the Negev, Be'er Sheva, Israel
    Search for articles by this author
Published:December 20, 2022DOI:https://doi.org/10.1016/j.jns.2022.120529

      Highlights

      • Data available at the time of admission may aid in stroke mortality prediction.
      • Machine learning has achieved great performance for stroke mortality prediction.
      • Age, high BMI and high NIHSS score are the most important predictors for mortality.
      • Deep learning has the potential to play an emerging role in stroke prognostication.

      Abstract

      Background and aims

      Accurate prognostication of stroke may help in appropriate therapy and rehabilitation planning. In the past few years, several machine learning (ML) algorithms were applied for prediction of stroke outcomes. We aimed to examine the performance of machine learning–based models for the prediction of mortality after stroke, as well as to identify the most prominent factors for mortality.

      Materials and methods

      We searched MEDLINE/PubMed and Web of Science databases for original publications on machine learning applications in stroke mortality prediction, published between January 1, 2011, and October 27, 2022. Risk of bias and applicability were evaluated using the tailored QUADAS-2 tool.

      Results

      Of the 1015 studies retrieved, 28 studies were included. Twenty-Five studies were retrospective. The ML models demonstrated a favorable range of AUC for mortality prediction (0.67–0.98). In most of the articles, the models were applied for short-term post stroke mortality. The number of explanatory features used in the models to predict mortality ranged from 5 to 200, with substantial overlap in the variables included. Age, high BMI and high NIHSS score were identified as important predictors for mortality. Almost all studies had a high risk of bias in at least one category and concerns regarding applicability.

      Conclusion

      Using machine learning, data available at the time of admission may aid in stroke mortality prediction. Notwithstanding, current research is based on few preliminary works with high risk of bias and high heterogeneity. Thus, future prospective, multicenter studies with standardized reports are crucial to firmly establish the usefulness of the algorithms in stroke prognostication.

      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 the Neurological Sciences
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Cho J.S.
        • Hu Z.
        • Fell N.
        • Heath G.W.
        • Qayyum R.
        • Sartipi M.
        Hospital discharge disposition of stroke patients in Tennessee.
        . 2018; 110: 594-600
      1. Counsell C, Dennis M. Systematic review of prognostic models in patients with acute stroke. 2001;159–70.

        • Id W.W.
        • Kiik M.
        • Peek N.
        • Curcin V.
        • Marshall I.J.
        • Rudd G.
        • et al.
        Plos one research article a systematic review of machine learning models for predicting outcomes of stroke with structured data.
        . 2020; 475 (Available from:): 1-16
        • Baykan K.
        • Kara Y.
        Predicting 10-day mortality in patients with strokes using neural networks and multivariate statistical methods € lya Tireli.
        MD x. 2014; : 1-7
        • Ong C.J.
        • Orfanoudaki A.
        • Zhang R.
        • Pierre F.
        • Caprasse M.
        • Hutch M.
        • et al.
        Machine learning and natural language processing methods to identify ischemic stroke, acuity and location from radiology reports.
        2020: 1-16 (Available from)
        • Fleuren L.M.
        • Klausch T.L.T.
        • Zwager C.L.
        • Schoonmade L.J.
        • Guo T.
        • Roggeveen L.F.
        • et al.
        Machine learning for the prediction of sepsis : a systematic review and meta - analysis of diagnostic test accuracy.
        Intensive Care Med. 2020; 46 (Available from:): 383-400
      2. Mangold C, Zoretic S, Thallapureddy K, Moreira A, Chorath K, Moreira A. Machine learning models for predicting neonatal mortality: a systematic review. 2021;394–405.

        • Vokinger K.N.
        • Feuerriegel S.
        • Kesselheim A.S.
        Mitigating bias in machine learning for medicine.
        Commun Med. 2021; (Available from:): 3-5
        • Moher D.
        • Liberati A.
        • Tetzlaff J.
        • Altman D.G.
        Academia and clinic annals of internal medicine preferred reporting items for systematic reviews and meta-analyses.
        . 2009; 151: 264-269
        • Moons K.G.M.
        • De Groot J.A.H.
        • Bouwmeester W.
        • Vergouwe Y.
        • Mallett S.
        Critical appraisal and data extraction for systematic reviews of prediction modelling studies : the CHARMS checklist.
        . 2014; 11: 10
        • Easton J.F.
        • Stephens C.R.
        • Angelova M.
        Risk factors and prediction of very short term versus short / intermediate term post-stroke mortality : a data mining approach.
        Comput Biol Med. 2014; 54 (Available from:): 199-210
        • Hicks S.A.
        • Strümke I.
        • Thambawita V.
        • Hammou M.
        • Riegler M.A.
        • Halvorsen P.
        • et al.
        On evaluation metrics for medical applications of artificial intelligence.
        Sci Rep. 2022; (0123456789. Available from:): 1-9
      3. Reitsma JB, Leeflang MMG, Sterne JAC, bossuyt pmm. research and reporting methods accuracy studies. 2011;(4).

        • Soffer S.
        • Klang E.
        • Shimon O.
        • Nachmias N.
        • Eliakim R.
        Deep learning for wireless capsule endoscopy : a systematic review and meta-analysis.
        Gastrointest Endosc. 2020; 92 (Available from:): 831-839.e8
      4. Nagendran M, Chen Y, Lovejoy CA, Gordon AC, Komorowski M, Harvey H, et al. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. 2020;1–12.

        • Ding L.
        • Mane R.
        • Wu Z.
        • Jiang Y.
        • Meng X.
        • Jing J.
        • et al.
        Articles Data-driven clustering approach to identify novel phenotypes using multiple biomarkers in acute ischaemic stroke : A retrospective, multicentre cohort study.
        eClinicalMedicine. 2022; 53 (. Available from:)101639
        • Kim J.T.
        • Kim N.R.
        • Choi S.H.
        • Oh S.
        • Park M.S.
        • Lee S.H.
        • et al.
        Neural network - based clustering model of ischemic stroke patients with a maximally distinct distribution of 1 - year vascular outcomes.
        Sci Rep. 2022; (0123456789. Available from:): 1-10
        • Lozano C.F.
        • Hervella P.
        • Abad V.M.
        • Yáñez M.R.
        • Garaboa S.S.
        • Dequidt I.L.
        • et al.
        Random forest - based prediction of stroke outcome.
        Sci Rep. 2021; (Available from:): 1-12
        • Abedi V.
        • Avula V.
        • Razavi S.
        • Bavishi S.
        • Chaudhary D.
        • Shahjouei S.
        • et al.
        Journal of the neurological sciences predicting short and long-term mortality after acute ischemic stroke using EHR.
        J Neurol Sci. 2021; 427 (Available from:)117560
        • Bacchi S.
        • Oakden-rayner L.
        • Menon D.K.
        • Jannes J.
        • Kleinig T.
        • Koblar S.
        Stroke prognostication for discharge planning with machine learning : a derivation study.
        J Clin Neurosci. 2020; 79 (Available from:): 100-103
      5. Ho KC, Speier W, El-saden S, Liebeskind DS, Saver JL, Bui AAT, et al. Predicting Discharge Mortality after Acute Ischemic Stroke Using Balanced Data Department of Bioengineering; 2 Medical Imaging Informatics. :1787–96.

        • Someeh N.
        • Jafarabadi M.A.
        • Shamshirgaran S.M.
        • Farzipoor F.
        The Outcome in Patients with Brain Stroke : A Deep Learning Neural Network Modeling.
        2020
        • Lucia A.
        • Fürstenberger C.
        • Daniela L.
        • Alfieri F.
        • Caroline M.
        • De Araújo M.
        • et al.
        Carotid intima media thickness measurements coupled with stroke severity strongly predict short - term outcome in patients with acute ischemic stroke : a machine learning study.
        Metab Brain Dis. 2021; (Available from:): 1747-1761
        • Bustamante A.
        • Giralt D.
        • Rubiera M.
        • Garcı T.
        • Montaner J.
        The impact of post-stroke complications on in-hospital mortality depends on stroke severity.
        . 2017; 2: 54-63
        • Scrutinio D.
        • Ricciardi C.
        • Donisi L.
        • Losavio E.
        • Battista P.
        • Guida P.
        • et al.
        Machine learning to predict mortality after rehabilitation among patients with severe stroke.
        Sci Rep. 2020; (0123456789. Available from:): 1-10
        • Rana S.
        • Luo W.
        • Tran T.
        • Venkatesh S.
        • Talman P.
        • Phan T.
        Application of machine learning techniques to identify data reliability and factors affecting outcome after stroke using electronic administrative records.
        . 2021; 12: 1-13
        • Wang W.
        • Rudd A.G.
        • Wang Y.
        • Curcin V.
        • Wolfe C.D.
        • Peek N.
        • et al.
        Risk prediction of 30 - day mortality after stroke using machine learning : a nationwide registry - based cohort study.
        BMC Neurol. 2022; (Available from:): 1-9
        • Berger K.
        • Karch A.
        Development and Validation of Prediction Models for Severe Complications after Acute Ischemic Stroke : A Study Based.
        2022
        • Amaya-pascasio L.
        • Mart P.
        • Rodr M.
        • Luis T.
        • Reche-lorite F.
        • Manuel J.
        Predictive Model and Mortality Risk Score During Admission for Ischaemic Stroke with Conservative Treatment.
        2022
        • Yçeli K.
        Prediction of mortality in stroke patients using multilayer perceptron neural networks Prediction of mortality in stroke patients using multilayer perceptron neural networks.
        . 2012; 42
        • Zhu H.
        A large-scale prospective study on functional ability and mortality following stroke based on hrs data set : implications for rehabilitation.
        . 2022; 13: 1-8
        • Park E.
        • Chang H.
        • Nam H.S.
        A Bayesian network model for predicting post-stroke outcomes with available risk factors.
        . 2018; 9: 1-11
        • Lucia A.
        • Fürstenberger C.
        • Daniela L.
        • Alfieri F.
        • Caroline M.
        • De Araújo M.
        • et al.
        Immune - inflammatory, coagulation, adhesion, and imaging biomarkers combined in machine learning models improve the prediction of death 1 year after ischemic stroke.
        Clin Exp Med. 2022; 22 (Available from:): 111-123
        • Zhang S.
        • Wang J.
        • Pei L.
        • Liu K.
        • Gao Y.
        • Fang H.
        • et al.
        Interpretability analysis of one-year mortality prediction for stroke patients based on deep neural network.
        . 2022; 26: 1903-1910
        • Liu W.
        • Ma W.
        • Bai N.
        • Li C.
        • Liu K.
        • Yang J.
        • et al.
        Identification of key predictors of hospital mortality in critically ill patients with embolic stroke using machine learning.
        . 2022; 0
        • Kurtz P.
        • Peres I.T.
        • Soares M.
        • Salluh J.I.F.
        • Bozza F.A.
        Hospital Length of Stay and 30 - Day Mortality Prediction in Stroke : A Machine Learning Analysis of 17, 000 ICU Admissions in Brazil.
        Neurocrit Care. 2022; 37 (Available from:): 313-321
        • Cheon S.
        • Kim J.
        The Use of Deep Learning to Predict Stroke Patient Mortality.
        2019
        • Flint A.C.
        • Cullen S.P.
        • Faigeles B.S.
        Predicting Long-Term Outcome after Endovascular Stroke Treatment: The Totaled Health Risks.
        2010: 2-6
        • Myint P.K.
        • Clark A.B.
        • Kwok C.S.
        • Davis J.
        • Durairaj R.
        • Dixit A.K.
        • et al.
        The SOAR (Stroke subtype, Oxford Community Stroke Project classification, Age, prestroke modified Rankin) score strongly predicts early outcomes in acute stroke.
        . 2014; 9: 278-283
        • Hospital JB
        The PLAN Score.
        172. 2012: 20
        • Saposnik G.
        • Kapral M.K.
        • Liu Y.
        • Hall R.
        • Donnell M.O.
        • Raptis S.
        • et al.
        A Risk Score to Predict Death Early After Hospitalization for an Acute Ischemic Stroke.
        2015
        • Drozdowska B.A.
        • Singh S.
        • Quinn T.J.
        Thinking about the future : a review of prognostic scales used in acute.
        Stroke. 2019; 10
        • Koennecke H.
        Factors Influencing in-Hospital Mortality and Morbidity in Patients Treated on a Stroke Unit.
        2011
        • Ziegler A.
        • Bluhmki E.
        • Hacke W.
        • Bath P.M.W.
        • Sacco R.L.
        • Diener H.C.
        • et al.
        Predicting Long-Term Outcome After Acute Ischemic Stroke A Simple Index Works in Patients From Controlled Clinical Trials.
        2008: 1821-1826
        • Weimar C.
        • Kraywinkel K.
        • Ziegler A.
        • Diener H.C.
        Age and National Institutes of Health Stroke Scale Score Within 6 Hours After Onset Are Accurate Predictors of Outcome After Cerebral Ischemia Development and External Validation of Prognostic Models.
        2003: 158-162
        • Che B.
        • Shen S.
        • Zhu Z.
        • Wang A.
        • Xu T.
        Education Level and Long-Term Mortality, Recurrent Stroke, and Cardiovascular Events in Patients With Ischemic Stroke.
        2020
        • Graham H.L.
        • Lac A.
        • Lee H.
        • Benton M.J.
        Predicting Long-Term Mortality, Morbidity, and Survival Outcomes Following a Cardiac Event : A Cardiac Rehabilitation Study.
        2019
        • Meinow B.
        • Ka I.
        • Parker M.G.
        • Thorslund M.
        The effect of the duration of follow-up in mortality analysis : the temporal pattern of different predictors.
        . 2004; 59: 181-189
      6. Https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc. No Title.

        • Food U.S.
        Software as a medical device (SaMD).
        Action Plan. 2021;
      7. . 2022; 28
        • Zhang Q.
        • Xie Y.
        • Ye P.
        • Pang C.
        Acute ischaemic stroke prediction from physiological time series patterns.
        2013: 280-286
        • Chung C.
        • Bamodu O.A.
        • Hong C.
        • Chan L.
        • Chiu H.
        Application of machine learning-based models to boost the predictive power of the SPAN index.
        Int J Neurosci. 2021; 0 (Available from:): 1-11
        • Zanotto B.S.
        • Paula A.
        • Etges S.
        • Bosco A.
        • Cortes E.G.
        • Ruschel R.
        • et al.
        Stroke outcome measurements from electronic medical records : cross-sectional study on the effectiveness of neural and nonneural classifiers corresponding author.
        . 2021; 9: 1-24
        • Hwangbo L.
        • Kang Y.J.
        • Kwon H.
        • Il Lee J.
        • Cho H.J.
        • Ko J.K.
        • et al.
        Stacking ensemble learning model to predict 6 - month mortality in ischemic stroke patients.
        Sci Rep. 2022; (Available from:): 1-9