Prediction of Brain Stroke Using Federated Learning

Rabia Tehseen; Uzma Omer; Rubab Javaid; Maham Mehr; Madiha Yousaf; Ayesha Zaheer

Authors

Rabia Tehseen University of Central Punjab, Lahore, Pakistan 57400
Uzma Omer University of Education, Lahore, Pakistan, 57400
Rubab Javaid University of Central Punjab, Lahore, Pakistan 57400
Maham Mehr University of Central Punjab, Lahore, Pakistan 57400
Madiha Yousaf University of Central Punjab, Lahore, Pakistan 57400
Ayesha Zaheer University of Central Punjab, Lahore, Pakistan 57400

Keywords:

Stroke, Machine Learning, CM, AUC, WV, Correlation Matrix

Abstract

Stroke often arises from an abrupt blockage in the blood vessels supplying the brain and heart. Detecting early warning signs of stroke can significantly reduce its impact. In this study, we propose an early prediction method for stroke using various Machine Learning (ML) techniques, considering factors such as hypertension, body mass index, heart disease, average glucose levels, smoking habits, prior stroke history, and age. These attributes, rich in information, were utilized to train three distinct classifiers: Logistic Regression, Decision Tree, and K-nearest neighbors for stroke prediction. In this study, Federated Learning (FL) has been applied to combine the ML models (Logistic Regression (LR), Decision Tree (DT), and K-Nearest Neighbors (KNN)) from distributed medical data sources while preserving patient privacy. By aggregating locally trained models from multiple hospitals or devices, FL ensures the robustness of the weighted voting classifier without requiring direct data sharing, thereby enhancing stroke prediction accuracy across diverse datasets. Subsequently, the results from these base classifiers were combined using a weighted voting approach to achieve the highest accuracy. Our study demonstrated an impressive accuracy rate of 97%, with the weighted voting classifier outperforming the individual base classifiers. This model proved to be the more accurate in predicting strokes. Additionally, the Area Under the Curve (AUC) value for the weighted voting classifier was notably high, and it exhibited the lowest false positive and false negative rates compared to other classifiers. Consequently, the weighted voting classifier emerged as an almost ideal tool for predicting strokes, offering valuable support to both physicians and patients in identifying and preventing potential stroke incidents.

References

S. Rahman, M. Hasan, and A. K. Sarkar, “Prediction of Brain Stroke using Machine Learning Algorithms and Deep Neural Network Techniques,” Eur. J. Electr. Eng. Comput. Sci., vol. 7, no. 1, pp. 23–30, Jan. 2023, doi: 10.24018/EJECE.2023.7.1.483.

O. Shobayo, O. Zachariah, M. O. Odusami, and B. Ogunleye, “Prediction of Stroke Disease with Demographic and Behavioural Data Using Random Forest Algorithm,” Anal. 2023, Vol. 2, Pages 604-617, vol. 2, no. 3, pp. 604–617, Aug. 2023, doi: 10.3390/ANALYTICS2030034.

P. Gahiwad, N. Deshmane, S. Karnakar, S. Mali, and R. Pise, “Brain Stroke Detection Using CNN Algorithm,” 2023 IEEE 8th Int. Conf. Converg. Technol. I2CT 2023, 2023, doi: 10.1109/I2CT57861.2023.10126125.

M. Singhal, M. Pruthi, N. Singhal, P. Nagrath, R. Jain, and A. Kumar, “Comparison of machine-learning and deep-learning algorithms for stroke prediction,” Edge-AI Healthc. Trends Futur. Perspect., pp. 115–128, Jan. 2023, doi: 10.1201/9781003244592-9/COMPARISON-MACHINE-LEARNING-DEEP-LEARNING-ALGORITHMS-STROKE-PREDICTION-MAYANK-SINGHAL-MANAN-PRUTHI-NIVEDITA-SINGHAL-PREETI-NAGRATH-RACHNA-JAIN-ASHISH-KUMAR.

S. Gupta and S. Raheja, “Stroke Prediction using Machine Learning Methods,” Proc. Conflu. 2022 - 12th Int. Conf. Cloud Comput. Data Sci. Eng., pp. 553–558, 2022, doi: 10.1109/CONFLUENCE52989.2022.9734197.

T. N. Deepthi, S. Sharmila, M. Swarna, M. Gouthami, and C. L. Akshaya, “Prediction of Brain Stroke in Human Beings using Machine Learning,” Proc. 2023 2nd Int. Conf. Electron. Renew. Syst. ICEARS 2023, pp. 1314–1320, 2023, doi: 10.1109/ICEARS56392.2023.10085128.

V. Bandi, D. Bhattacharyya, and D. Midhunchakkravarthy, “Prediction of brain stroke severity using machine learning,” Rev. d’Intelligence Artif., vol. 34, no. 6, pp. 753–761, Dec. 2020, doi: 10.18280/RIA.340609.

G. Sailasya and G. L. A. Kumari, “Analyzing the Performance of Stroke Prediction using ML Classification Algorithms,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 6, pp. 539–545, 2021, doi: 10.14569/IJACSA.2021.0120662.

M. J. Uddin Chowdhury, A. Hussan, D. A. Islam Hridoy, and A. S. Sikder, “Incorporating an Integrated Software System for Stroke Prediction using Machine Learning Algorithms and Artificial Neural Network,” 2023 IEEE 13th Annu. Comput. Commun. Work. Conf. CCWC 2023, pp. 222–228, 2023, doi: 10.1109/CCWC57344.2023.10099245.

“Performance Analysis of Machine Learning Approaches for Stroke Prediction in Healthcare | IEEE Conference Publication | IEEE Xplore.” Accessed: Dec. 13, 2024. [Online]. Available: https://ieeexplore.ieee.org/document/10112284

S. Dev, H. Wang, C. S. Nwosu, N. Jain, B. Veeravalli, and D. John, “A predictive analytics approach for stroke prediction using machine learning and neural networks,” Healthc. Anal., vol. 2, p. 100032, Nov. 2022, doi: 10.1016/J.HEALTH.2022.100032.

S. Mushtaq and K. S. Saini, “A Review on Predicting Brain Stroke using Machine Learning,” Int. Conf. Comput. Sustain. Glob. Dev., 2023.

N. Victor, S. Bhattacharya, P. K. R. Maddikunta, F. M. Alotaibi, T. R. Gadekallu, and R. H. Jhaveri, “FL-PSO: A Federated Learning approach with Particle Swarm Optimization for Brain Stroke Prediction,” Proc. - 23rd IEEE/ACM Int. Symp. Clust. Cloud Internet Comput. Work. CCGridW 2023, pp. 33–38, 2023, doi: 10.1109/CCGRIDW59191.2023.00020.

R. Kumari and H. Garg, “Interpretation and Analysis of Machine Learning Models for Brain Stroke Prediction,” 2023 6th Int. Conf. Inf. Syst. Comput. Networks, ISCON 2023, 2023, doi: 10.1109/ISCON57294.2023.10112188.

A. S. Chandrabhatla, E. A. Kuo, J. D. Sokolowski, R. T. Kellogg, M. Park, and P. Mastorakos, “Artificial Intelligence and Machine Learning in the Diagnosis and Management of Stroke: A Narrative Review of United States Food and Drug Administration-Approved Technologies,” J. Clin. Med., vol. 12, no. 11, Jun. 2023, doi: 10.3390/JCM12113755.

S. Zhang et al., “Research Progress of Deep Learning in the Diagnosis and Prevention of Stroke,” Biomed Res. Int., vol. 2021, p. 5213550, 2021, doi: 10.1155/2021/5213550.

B. Akter, A. Rajbongshi, S. Sazzad, R. Shakil, J. Biswas, and U. Sara, “A Machine Learning Approach to Detect the Brain Stroke Disease,” Proc. - 4th Int. Conf. Smart Syst. Inven. Technol. ICSSIT 2022, pp. 897–901, 2022, doi: 10.1109/ICSSIT53264.2022.9716345.

I. R. Chavva et al., “Deep Learning Applications for Acute Stroke Management,” Ann. Neurol., vol. 92, no. 4, pp. 574–587, Oct. 2022, doi: 10.1002/ANA.26435.

Ferdib-Al-Islam and M. Ghosh, “An Enhanced Stroke Prediction Scheme Using Smote and Machine Learning Techniques,” 2021 12th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2021, 2021, doi: 10.1109/ICCCNT51525.2021.9579648.

M. Kaur, S. R. Sakhare, K. Wanjale, and F. Akter, “[Retracted] Early Stroke Prediction Methods for Prevention of Strokes,” Behav. Neurol., vol. 2022, no. 1, p. 7725597, Jan. 2022, doi: 10.1155/2022/7725597.

P. Premisha, S. Prasanth, M. Kanagarathnam, and K. Banujan, “An Ensemble Machine Learning Approach for Stroke Prediction,” Proc. - Int. Res. Conf. Smart Comput. Syst. Eng. SCSE 2022, pp. 165–170, 2022, doi: 10.1109/SCSE56529.2022.9905215.

“Machine Learning for Brain Stroke: A Review - ScienceDirect.” Accessed: Dec. 13, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/abs/pii/S1052305720305802

B. R. Gaidhani, R. Rajamenakshi, and S. Sonavane, “Brain stroke detection using convolutional neural network and deep learning models,” 2019 2nd Int. Conf. Intell. Commun. Comput. Tech. ICCT 2019, pp. 242–249, Sep. 2019, doi: 10.1109/ICCT46177.2019.8969052.

H. Zhang, “Stroke Prediction Based on Support Vector Machine,” Highlights Sci. Eng. Technol., vol. 31, pp. 53–59, Feb. 2023, doi: 10.54097/HSET.V31I.4812.

A. P. . Rohit, M. U. Chowdary, G. B. . Ashish, V. Anitha, and S. Sana, “ML APPROACH FOR BRAIN STROKE PREDICTION USING IST DATABASE,” Int. J. Eng. Appl. Sci. Technol., vol. 7, no. 10, pp. 72–75, Feb. 2023, doi: 10.33564/IJEAST.2023.V07I10.008.

A. Subudhi, P. Dash, M. Mohapatra, R. S. Tan, U. R. Acharya, and S. Sabut, “Application of Machine Learning Techniques for Characterization of Ischemic Stroke with MRI Images: A Review,” Diagnostics 2022, Vol. 12, Page 2535, vol. 12, no. 10, p. 2535, Oct. 2022, doi: 10.3390/DIAGNOSTICS12102535.

D. V. Desai, T. Jain, and P. Tiwari, “Supervised Machine Learning Approaches for Brain Stroke Detection,” 11th Int. Conf. Internet Everything, Microw. Eng. Commun. Networks, IEMECON 2023, 2023, doi: 10.1109/IEMECON56962.2023.10092374.

S. Kanaga Suba Raja, B. Chandra, K. Kausalya, R. M. Ciddarth, and V. Gokul Ranjith, “Prognosis of Stroke using Machine Learning Algorithms,” Proc. - 7th Int. Conf. Comput. Methodol. Commun. ICCMC 2023, 2023, doi: 10.1109/ICCMC56507.2023.10084158.

S. Mushtaq, K. S. Saini, and S. Bashir, “Machine Learmusht for Brain Stroke Prediction,” 2023 Int. Conf. Disruptive Technol. ICDT 2023, pp. 401–408, 2023, doi: 10.1109/ICDT57929.2023.10151148.

G. Yang, M. Xu, W. Chen, X. Qiao, H. Shi, and Y. Hu, “A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhage,” Front. Neurol., vol. 14, 2023, doi: 10.3389/FNEUR.2023.1139048.

D. V. V. V. C. Mouli, “Artificial Intelligence Enabled Framework for Automatic Brain Stroke Detection,” Proc. 10th Int. Conf. Signal Process. Integr. Networks, SPIN 2023, pp. 659–664, 2023, doi: 10.1109/SPIN57001.2023.10116629.

S. Ruksakulpiwat et al., “Machine learning-based patient classification system for adults with stroke: A systematic review,” Chronic Illn., vol. 19, no. 1, pp. 26–39, Mar. 2023, doi: 10.1177/17423953211067435.

N. Biswas, K. M. M. Uddin, S. T. Rikta, and S. K. Dey, “A comparative analysis of machine learning classifiers for stroke prediction: A predictive analytics approach,” Healthc. Anal., vol. 2, p. 100116, Nov. 2022, doi: 10.1016/J.HEALTH.2022.100116.

H. Al-Zubaidi, M. Dweik, and A. Al-Mousa, “Stroke Prediction Using Machine Learning Classification Methods,” Proc. - 2022 23rd Int. Arab Conf. Inf. Technol. ACIT 2022, vol. 2022-January, 2022, doi: 10.1109/ACIT57182.2022.10022050.

A. Diker, A. Elen, and A. Subasi, “Brain stroke detection from computed tomography images using deep learning algorithms,” Appl. Artif. Intell. Med. Imaging, pp. 207–222, Jan. 2023, doi: 10.1016/B978-0-443-18450-5.00013-X.

K. Wang et al., “A machine learning model for visualization and dynamic clinical prediction of stroke recurrence in acute ischemic stroke patients: A real-world retrospective study,” Front. Neurosci., vol. 17, 2023, doi: 10.3389/FNINS.2023.1130831.

“(PDF) An Explainable Machine Learning Framework for Early Detection of Stroke.” Accessed: Dec. 13, 2024. [Online]. Available: https://www.researchgate.net/publication/373424278_An_Explainable_Machine_Learning_Framework_for_Early_Detection_of_Stroke

S. C. Manjunath, “Predicting Stroke at Adulthood Using Machine Learning Techniques,” Jan. 2023.

S. O. Abdulsalam, M. O. Arowolo, and O. Ruth, “Stroke Disease Prediction Model Using ANOVA with Classification Algorithms,” pp. 117–134, 2023, doi: 10.1007/978-981-99-0369-6_8.

V. Kumar, V. S., Thanmai, B., ManognaVyshnavi, A., Sujitha, I., & Jhansi, “Prediction of Stroke Risk Using a Hybrid Deep Transfer Learning Framework,” J. Eng. Sci., vol. 14, no. 04, 2023.

A. Faskhutdinova, D. Grigorieva, B. Garafutdinov, and V. Mokshin, “Investigation of Machine Learning Methods for Stroke Prediction,” Proc. - 9th IEEE Int. Conf. Inf. Technol. Nanotechnology, ITNT 2023, 2023, doi: 10.1109/ITNT57377.2023.10139121.

A. K. Uttam, “Analysis of Uneven Stroke Prediction Dataset using Machine Learning,” Proc. - 2022 6th Int. Conf. Intell. Comput. Control Syst. ICICCS 2022, pp. 1209–1213, 2022, doi: 10.1109/ICICCS53718.2022.9788309.

C. Sharma, S. Sharma, M. Kumar, and A. Sodhi, “Early Stroke Prediction Using Machine Learning,” 2022 Int. Conf. Decis. Aid Sci. Appl. DASA 2022, pp. 890–894, 2022, doi: 10.1109/DASA54658.2022.9765307.

E. Dritsas and M. Trigka, “Stroke Risk Prediction with Machine Learning Techniques,” Sensors (Basel)., vol. 22, no. 13, p. 4670, Jul. 2022, doi: 10.3390/S22134670.

H. M. Xia and R. Ramezani, “Analyzing the Performance of TabTransformer in Brain Stroke Prediction,” J. Student Res., vol. 12, no. 1, Feb. 2023, doi: 10.47611/jsrhs.v12i1.3935.

S. Paliwal, S. Parveen, M. A. Alam, and J. Ahmed, “Improving Brain Stroke Prediction through Oversampling Techniques: A Comparative Evaluation of Machine Learning Algorithms,” Jun. 2023, doi: 10.20944/PREPRINTS202306.1444.V1.

P. Savar Mattas, “Brain Stroke Prediction Using Machine Learning,” Int. J. Res. Publ. Rev., vol. 03, no. 12, pp. 711–722, 2022, doi: 10.55248/GENGPI.2022.31211.

T. Liu, W. Fan, and C. Wu, “A hybrid machine learning approach to cerebral stroke prediction based on imbalanced medical dataset,” Artif. Intell. Med., vol. 101, p. 101723, Nov. 2019, doi: 10.1016/J.ARTMED.2019.101723.

“Stroke Prediction Dataset.” Accessed: Dec. 13, 2024. [Online]. Available: https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset