Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug 25;15(1):31215.
doi: 10.1038/s41598-025-14358-5.

Optimizing brain stroke detection with a weighted voting ensemble machine learning model

Reeta Samuel  1 , Thanapal Pandi  2
Affiliations

Optimizing brain stroke detection with a weighted voting ensemble machine learning model

Reeta Samuel et al. Sci Rep. .

Abstract

Brain stroke is a medical trauma that occurs when there is an impairment or decrease in blood circulation to a particular part of the brain, causing adjacent brain cells to die. Stroke diagnosis after an event is an ineffective method; other more labour-intensive and costly procedures exist for stroke diagnosis. This method involves directing a machine learning algorithm to a marked dataset to identify samples and irregularities indicative of stroke occurrence. This study focused on developing an ensemble machine learning model to predict brain stroke. The model combined the predictions of multiple individualistic classifiers, including random forest, eXtreme gradient boosting, and histogram-based gradient boosting, to improve accuracy. The proposed weighted voting-based ensemble (WVE) classifier model achieved an accuracy of 92.31% on a private stroke prediction dataset. The pre-assessment of stroke risk diagnosis, as suggested in this study, enables many people to take preventive actions well in advance, thereby lowering fatal effects. Our proposed method presents a feasible option for the early or initial diagnosis of stroke, as traditional methods, such as computed tomography (CT) scans and magnetic resonance imaging (MRIs), are time-consuming and costly. Future research could explore the use of intelligence-based optimization to enhance classification accuracy and address this limitation.

Keywords: Brain stroke detection; EXtreme gradient boosting (XGBoost); Histogram-based gradient boosting (HGB); Machine learning (ML); Random forest (RF); Weighted voting.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Ethics: A statement to confirm that all the methods and experiments conducted were purely computational and did not involve any human subjects directly. The names and personal details of the patients were highly confidential. All methods were carried out in accordance with relevant guidelines and regulations. All experimental protocols were approved by the KC Multi specialty Hospital in Chennai, India. Consent for publication: We confirm that informed consent was obtained from all subjects and/or their legal guardian(s).

Figures

Fig. 1
Fig. 1
Risk factors for stroke.
Fig. 2
Fig. 2
Proposed weighted voting-based ensemble classifier model.
Fig. 3
Fig. 3
Random forest classifier.
Fig. 4
Fig. 4
Histogram-based gradient boosting structure.
Fig. 5
Fig. 5
Overview of the implementation process.
Fig. 6
Fig. 6
Comparison of the proposed construction with alternative models.
Fig. 7
Fig. 7
An analysis of the proposed model’s precision, recall, and F1-score.
Fig. 8
Fig. 8
Accuracy and log loss interpretation.
Fig. 9
Fig. 9
Feature importance ranking.
None
Algorithm 1 Proposed model
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Yüksel, M. M. et al. Low-intensity focused ultrasound neuromodulation for stroke recovery: A novel deep brain stimulation approach for neurorehabilitation?. IEEE Open J. Eng. Med. Biol.4, 300–318. 10.1109/ojemb.2023.3263690 (2023). - PMC - PubMed
    1. Polat, Ö., Dokur, Z. & Ölmez, T. Classification of brain strokes using divergence-based convolutional neural networks. Biomed. Signal Process. Control93, 106193. 10.1016/j.bspc.2024.106193 (2024).
    1. Goni, M. R., Ruhaiyem, N. I. R., Mustapha, M., Achuthan, A. & Che Mohd Nassir, C. M. N. Brain vessel segmentation using deep learning—a review. IEEE Access10, 111322–111336. 10.1109/access.2022.3214987 (2022).
    1. Baek, H. et al. Deep cerebellar low-intensity focused ultrasound stimulation restores interhemispheric balance after ischemic stroke in mice. IEEE Trans. Neural Syst. Rehabil. Eng.28(9), 2073–2079. 10.1109/tnsre.2020.3002207 (2020). - PubMed
    1. Guo, T. et al. Pulsed transcranial ultrasound stimulation immediately after the ischemic brain injury is neuroprotective. IEEE Trans. Biomed. Eng.62(10), 2352–2357. 10.1109/tbme.2015.2427339 (2015). - PubMed

LinkOut - more resources