Predicting Clinical Outcomes in Acute Ischemic Stroke Patients Undergoing Endovascular Thrombectomy with Machine Learning: A Systematic Review and Meta-analysis

Purpose Conventional predictive models are based on a combination of clinical and neuroimaging parameters using traditional statistical approaches. Emerging studies have shown that the machine learning (ML) prediction models with multiple pretreatment clinical variables have the potential to accurat...

Full description

Saved in:
Bibliographic Details
Published in:Clinical neuroradiology (Munich) 2021-12, Vol.31 (4), p.1121-1130
Main Authors: Teo, Yao Hao, Lim, Isis Claire Z. Y., Tseng, Fan Shuen, Teo, Yao Neng, Kow, Cheryl Shumin, Ng, Zi Hui Celeste, Chan Ko Ko, Nyein, Sia, Ching-Hui, Leow, Aloysius S. T., Yeung, Wesley, Kong, Wan Yee, Chan, Bernard P. L., Sharma, Vijay K., Yeo, Leonard L. L., Tan, Benjamin Y. Q.
Format: Article
Language:English
Subjects:
Medicine
Medicine & Public Health
Neurology
Neuroradiology
Neurosurgery
Original Article
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Purpose Conventional predictive models are based on a combination of clinical and neuroimaging parameters using traditional statistical approaches. Emerging studies have shown that the machine learning (ML) prediction models with multiple pretreatment clinical variables have the potential to accurately prognosticate the outcomes in acute ischemic stroke (AIS) patients undergoing thrombectomy, and hence identify patients suitable for thrombectomy. This article summarizes the published studies on ML models in large vessel occlusion AIS patients undergoing thrombectomy. Methods We searched electronic databases including PubMed from 1 January 2000 up to 14 October 2019 for studies that evaluated ML algorithms for the prediction of outcomes in stroke patients undergoing thrombectomy. We then used random-effects bivariate meta-analysis models to summarize the studies. Results We retained a total of five studies that evaluated ML (4 support vector machine, 1 decision tree model) with a combined cohort of 802 patients. The prevalence of good functional outcome defined by 90-day mRS of 0–2 when available. Random effects model demonstrated that the AUC was 0.846 (95% confidence interval, CI 0.686–0.902). A pooled diagnostic odds ratio of 12.6 was computed. The pooled sensitivity and specificity were 0.795 (95% CI 0.651–0.889) and 0.780 (95% CI 0.634–0.879), respectively. Conclusion ML may be useful as an adjunct to clinical assessment to predict functional outcomes in AIS patients undergoing thrombectomy, and hence identify suitable patients for treatment. Further studies validating ML models in large multicenter cohorts are necessary to explore this further.
ISSN:1869-1439
1869-1447
DOI:10.1007/s00062-020-00990-3