Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Oct 31, 2023
Open Peer Review Period: Oct 30, 2023 - Dec 25, 2023
Date Accepted: Nov 26, 2024
(closed for review but you can still tweet)
Machine learning for the early prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage: a systematic review and meta-analysis
ABSTRACT
Background:
Delayed cerebral ischemia (DCI) is a primary contributor to death after subarachnoid hemorrhage (SAH), with a very high incidence. Hence, it is urgent to early determine the risk of DCI.
Objective:
Currently, some studies have attempted to apply machine learning (ML) models for early noninvasive prediction of DCI, however, its predictive accuracy still needs further discussion. Therefore, this study intended to discuss the performance of ML for DCI prediction.
Methods:
Pubmed, Cochrane, Embase, and Web of Science were systematically searched up to 18 May 2023. We assessed the risk of bias in the included studies using the PROBAST and performed subgroup analyses by different types of models.
Results:
We finally included 48 studies containing 16,294 patients with SAH, involving 71 ML models, with logistic regression as the main model type. The results revealed that in the validation set, the pooled c-index, sensitivity, and specificity of all models were 0.767 (95% CI: 0.741~0.793), 0.66 (95% CI: 0.53~0.77), and 0.78 (95% CI: 0.71~0.84), respectively; while those of logistic regression models were 0.757 (95% CI: 0.715~0.800), 0.59 (95% CI: 0.57~0.80), and 0.80 (95% CI: 0.71~0.87), respectively.
Conclusions:
ML models appear to have relatively desirable power for early noninvasive prediction of DCI after SAH, however, it remains challenging to enhance the prediction sensitivity. Therefore, efficient, noninvasive, or minimally invasive, low-cost predictors should be further explored in subsequent studies to improve the accuracy of ML models. Clinical Trial: CRD42023438399
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.