Article Text

Download PDFPDF
Machine learning for clinical outcome prediction in cerebrovascular and endovascular neurosurgery: systematic review and meta-analysis
  1. Haydn Hoffman1,
  2. Jason J Sims2,
  3. Violiza Inoa-Acosta1,3,
  4. Daniel Hoit4,
  5. Adam S Arthur1,4,
  6. Dan Y Draytsel5,
  7. YeonSoo Kim5,
  8. Nitin Goyal1,3
    1. 1Semmes-Murphey Neurologic and Spine Institute, Memphis, Tennessee, USA
    2. 2The University of Tennessee Health Science Center, Memphis, Tennessee, USA
    3. 3Neurology, University of Tennessee Health Science Center, Memphis, Tennessee, USA
    4. 4Neurosurgery, University of Tennessee Health Science Center, Memphis, Tennessee, USA
    5. 5SUNY Upstate Medical University, Syracuse, New York, USA
    1. Correspondence to Dr Haydn Hoffman, Semmes-Murphey Neurologic and Spine Institute, Memphis, Tennessee, USA; hhoffman{at}semmes-murphey.com

    Abstract

    Background Machine learning (ML) may be superior to traditional methods for clinical outcome prediction. We sought to systematically review the literature on ML for clinical outcome prediction in cerebrovascular and endovascular neurosurgery.

    Methods A comprehensive literature search was performed, and original studies of patients undergoing cerebrovascular surgeries or endovascular procedures that developed a supervised ML model to predict a postoperative outcome or complication were included.

    Results A total of 60 studies predicting 71 outcomes were included. Most cohorts were derived from single institutions (66.7%). The studies included stroke (32), subarachnoid hemorrhage ((SAH) 16), unruptured aneurysm (7), arteriovenous malformation (4), and cavernous malformation (1). Random forest was the best performing model in 12 studies (20%) followed by XGBoost (13.3%). Among 42 studies in which the ML model was compared with a standard statistical model, ML was superior in 33 (78.6%). Of 10 studies in which the ML model was compared with a non-ML clinical prediction model, ML was superior in nine (90%). External validation was performed in 10 studies (16.7%). In studies predicting functional outcome after mechanical thrombectomy the pooled area under the receiver operator characteristics curve (AUROC) of the test set performances was 0.84 (95% CI 0.79 to 0.88). For studies predicting outcomes after SAH, the pooled AUROCs for functional outcomes and delayed cerebral ischemia were 0.89 (95% CI 0.76 to 0.95) and 0.90 (95% CI 0.66 to 0.98), respectively.

    Conclusion ML performs favorably for clinical outcome prediction in cerebrovascular and endovascular neurosurgery. However, multicenter studies with external validation are needed to ensure the generalizability of these findings.

    • Stroke
    • Technology
    • Aneurysm

    Data availability statement

    Data are available upon reasonable request.

    Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    Data are available upon reasonable request.

    View Full Text

    Footnotes

    • X @haydnhoffmanmd, @InoaVioliza, @AdamArthurMD

    • Contributors HH: conceptualization, methodology, investigation, formal analysis, writing, guarantor. JJS: investigation, data curation, writing - reviewing and editing. VI-A: writing - reviewing and editing, supervision, project administration. DH: writing - reviewing and editing, supervision, project administration. ASA: writing - reviewing and editing, supervision, project administration. DYD: investigation, data curation, writing - reviewing and editing. YK: investigation, data curation, writing - reviewing and editing. NG: conceptualization, methodology, supervision, project administration.

    • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

    • Competing interests None declared.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.