You are here

Article Text

Article menu
Clinical neurology
Original research
An explainable machine learning model for predicting the outcome of ischemic stroke after mechanical thrombectomy
  1. Zhelv Yao1,2,3,
  2. Chenglu Mao1,2,3,
  3. Zhihong Ke2,3,4,
  4. Yun Xu1,2,3
  1. 1 Department of Neurology, Nanjing University Medical School Affiliated Nanjing Drum Tower Hospital, Nanjing, Jiangsu, China
  2. 2 Jiangsu Key Laboratory for Molecular Medicine, Nanjing University Medical School, Nanjing, China
  3. 3 Nanjing Medicine Center For Neurological Diseases, Nanjing, China
  4. 4 Department of Neurology, Nanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing, China
  1. Correspondence to Dr Yun Xu, Neurology, Nanjing University Medical School Affiliated Nanjing Drum Tower Hospital, Nanjing, China; xuyun20042001{at}aliyun.com

Abstract

Background There is high variability in the clinical outcomes of patients with acute ischemic stroke (AIS) after mechanical thrombectomy (MT).

Methods 217 consecutive patients with anterior circulation large vessel occlusion who underwent MT between August 2018 and January 2022 were analysed. The primary outcome was functional independence defined as a modified Rankin Scale score of 0–2 at 3 months. In the derivation cohort (August 2018 to December 2020), 7 ensemble ML models were trained on 70% of patients and tested on the remaining 30%. The model’s performance was further validated on the temporal validation cohort (January 2021 to January 2022). The SHapley Additive exPlanations (SHAP) framework was applied to interpret the prediction model.

Results Derivation analyses generated a 9-item score (PFCML-MT) comprising age, National Institutes of Health Stroke Scale score, collateral status, and postoperative laboratory indices (albumin-to-globulin ratio, estimated glomerular filtration rate, blood neutrophil count, C-reactive protein, albumin and serum glucose levels). The area under the curve was 0.87 for the test set and 0.84 for the temporal validation cohort. SHAP analysis further determined the thresholds for the top continuous features. This model has been translated into an online calculator that is freely available to the public (https://zhelvyao-123-60-sial5s.streamlitapp.com).

Conclusions Using ML and readily available features, we developed an ML model that can potentially be used in clinical practice to generate real-time, accurate predictions of the outcome of patients with AIS treated with MT.

  • Blood Flow
  • Intervention
  • Stroke
  • Thrombectomy

Data availability statement

Data are available upon reasonable request.

https://creativecommons.org/licenses/by/4.0/

This is an open access article distributed in accordance with the Creative Commons Attribution 4.0 Unported (CC BY 4.0) license, which permits others to copy, redistribute, remix, transform and build upon this work for any purpose, provided the original work is properly cited, a link to the licence is given, and indication of whether changes were made. See: https://creativecommons.org/licenses/by/4.0/.

https://doi.org/10.1136/jnis-2022-019598

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

    Supplementary materials

    • Supplementary Data

      This web only file has been produced by the BMJ Publishing Group from an electronic file supplied by the author(s) and has not been edited for content.

    Footnotes

    • Contributors ZY contributed substantially to study design, data acquisition, analysis, interpretation, and manuscript drafting. CM and ZK contributed to data acquisition and analysis. YX contributed to study concept and design, and critical revision of the manuscript for important intellectual content. All authors gave their final approval of the manuscript to be published. YX is the guarantor responsible for the overall content.

    • Funding This research was supported by the National Natural Science Foundation of China (81920108017, 82130036), the Key Research and Development Program of Jiangsu Province of China (BE2020620), Jiangsu Province Key Medical Discipline (ZDXKA2016020), and the National Science and Technology Innovation 2030 -- Major program of "Brain science and brain-like research" (2022ZD0211800).

    • 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.