Stroke Detection System Using Machine Learning
DOI:
https://doi.org/10.67308/irjist.082Keywords:
Stroke Detection, Machine Learning, Healthcare Analytics, Random Forest, Support Vector Machine, SMOTE, Feature SelectionAbstract
Stroke is one of the leading causes of death and long-term disability worldwide, making accurate and timely risk prediction important for improving patient outcomes and supporting preventive healthcare. This paper presents a comprehensive machine learning-based stroke detection system that uses clinical and demographic patient information for probabilistic risk assessment. The system was developed using the Kaggle Stroke Prediction Dataset containing 5,110 patient records and 11 clinical features. To address class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied to the training data, while missing BMI values were handled using median imputation, followed by feature encoding and scaling. Six supervised classification algorithms—Random Forest, Decision Tree, Support Vector Machine (SVM), Logistic Regression, Multi-layer Perceptron (MLP), and K-Nearest Neighbour (KNN)—were trained and evaluated. Feature selection was performed using correlation analysis followed by Recursive Feature Elimination with Cross-Validation (RFECV). On the held-out test set, the Random Forest classifier achieved the best overall performance, with an accuracy of 95.60%, precision of 70.00%, recall of 14.29%, F1-score of 23.73%, and ROC-AUC of 0.8465. The proposed framework further integrates SHAP-based patient-level explainability and a Flask REST API with healthcare interoperability support. The system provides a modular framework for stroke risk prediction and can be further extended toward IoT-based monitoring, federated learning, multimodal clinical data integration, and prospective clinical validation.
Downloads
References
[1] World Health Organization, “The top 10 causes of death,” WHO Technical Report, Geneva, Switzerland, Dec. 2020. [Online]. Available: https://www.who.int
[2] V. L. Feigin, B. Norrving, and G. A. Mensah, “Global burden of stroke,” Circ. Res., vol. 120, no. 3, pp. 439–448, Feb. 2021. doi: 10.1161/CIRCRESAHA.116.308413
[3] N. Srivastava, S. Agarwal, R. Sharma, and P. K. Gupta, “Machine learning approaches for stroke prediction: A systematic review and meta-analysis,” J. Med. Syst., vol. 46, no. 2, pp. 1–18, Jan. 2022.
[4] A. Kaur, S. S. Gill, and P. Kumar, “Comparative analysis of machine learning algorithms for ischemic stroke prediction,” IEEE Access, vol. 10, pp. 34891–34904, Mar. 2022.
[5] M. Uddin, Y. Wang, and M. Woodbury-Smith, “Artificial intelligence for precision medicine in neurodevelopmental disorders,” npj Digit. Med., vol. 3, no. 1, p. 14, 2020.
[6] T. Elsayed, A. Hassan, and M. El-Rashidy, “Early stroke detection using machine learning: A comparative study,” Comput. Mater. Contin., vol. 74, no. 1, 2023.
[7] B. Choi, J. Lee, D. Kim, and S. Park, “Stroke risk prediction with machine learning: Korean genome study,” PLoS ONE, vol. 17, no. 4, Art. no. e0268282, Apr. 2022.
[8] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” J. Artif. Intell. Res., vol. 16, pp. 321–357, 2002.
[9] D. Hung, T. Nguyen, and H. Le, “Stroke prediction using ensemble learning with feature selection on imbalanced data,” Appl. Sci., vol. 12, no. 9, p. 4622, 2022.
[10] M. A. Rahman and S. I. Islam, “Stroke prediction using machine learning with class imbalance correction,” Healthcare, vol. 10, no. 8, p. 1596, Aug. 2022.
[11] P. Thaiparnit, K. Krissanaphan, and W. Chaiporndej, “Comparative performance of classification algorithms in stroke prediction,” Inform. Med. Unlocked, vol. 30, p. 100941, 2022.
[12] S. Sachdeva, A. Verma, and R. Gupta, “Feature selection methods for stroke prediction: A review,” Artif. Intell. Rev., vol. 56, pp. 7219–7256, 2023.
[13] J. Yu, S. Park, S. H. Kwon, C.-M. Cho, H. S. Kwon, and K. Lee, “AI-based stroke disease prediction using real-time clinical data,” Electronics, vol. 11, no. 15, p. 2326, 2022.
[14] R. Islam, A. Abusham, and M. A. Rahman, “Explainable AI-based stroke risk prediction using SHAP,” Diagnostics, vol. 12, no. 11, p. 2816, 2022.
[15] W. Guo, K. Ge, J. Chen, and X. Zhang, “Federated learning for stroke risk prediction across multi-institutional networks,” IEEE J. Biomed. Health Inform., vol. 27, no. 4, pp. 1832–1841, 2023.
[16] H. Zhao, X. Liu, Y. Zhang, and L. Wang, “IoT-enabled real-time stroke early warning with edge AI,” IEEE Internet Things J., vol. 10, no. 18, pp. 15921–15932, 2023.
[17] A. Patel, D. Singh, and R. Menon, “Deep learning approaches for multimodal stroke prognosis,” Comput. Biol. Med., vol. 158, p. 106812, 2023.
[18] J. Nandwalkar, V. Patil, Y. Waykole, and D. Prasad, “BioMedLink: Health Records at Your Fingertips,” Int. Res. J. Innov. Sci. Technol., vol. 1, no. 2, pp. 131–137, 2026, doi: 10.67308/irjist.041.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dipti D. Gaikwad, Komal B. Dandge, Gaurav R. Bhalekar, Dr. Shrikant J. Honade, Dr. Ganesh B. Dongre (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the International Research Journal of Innovation in Science and Technology (IRJIST) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Authors retain the copyright of their work and grant the journal the right of first publication. Proper attribution to the authors and the journal is required for any reuse of the published content.
