Fusing Attention and Convolution: A Hybrid Model for Brain Stroke Prediction

R. Bhuvanya; T. Kujani; K. Sivakumar

doi:10.4108/eetsis.7022

Authors

R. Bhuvanya Sri Ramachandra Institute of Higher Education and Research
T. Kujani Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology
K. Sivakumar Nehru Institute of Engineering and Technology

DOI:

https://doi.org/10.4108/eetsis.7022

Keywords:

AdaGrad, Brain Stroke detection, CNN, Machine Learning, Transformer

Abstract

INTRODUCTION: A stroke, a sudden interruption of blood flow to the brain, is a leading cause of disability and death. Early diagnosis is paramount for minimizing brain damage and maximizing treatment effectiveness.

OBJECTIVES: Traditional diagnostic methods can be time-consuming and have limited Accuracy.

METHODS: This study investigates the efficacy of various machine-learning models for stroke prediction. Specifically, it compares established models like K-Nearest Neighbor, Artificial Neural Network, Long Short Term Memory (LSTM), and stacked LSTM with a newly proposed Transformer Convolutional Neural Network (TCNN) architecture, which fuses Transformer and Convolutional neural network (CNN) models.

RESULTS: The TCNN demonstrates significant promise, achieving a superior accuracy of 98% when optimized with the AMSGrad optimizer.

CONCLUSION: These findings suggest that the TCNN architecture has the potential to revolutionize stroke prediction accuracy compared to existing methods, potentially leading to improved patient outcomes.

References

[1] Dritsas E, Trigka M. Stroke risk prediction with machine learning techniques. ensors. 022; 22(13):4670.

[2] Luan Y, Lin S, "Research on Text Classification Based on CNN and LSTM," 2019 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA); Dalian, China, 2019, pp. 352-355, doi: 10.1109/ICAICA.2019.8873454.

[3] Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, Cistac P, Rault T, Louf R, Funtowicz M. Davison J. Transformers: State-of-the-art natural language processing. n Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations, 2020. 38-45.

[4] Bathla P, Kumar R. A hybrid system to predict brain stroke using a combined feature selection and classifier. Intelligent Medicine. 024; 4(02):75-82.

[5] Choi Y A, Park S J, Jun J A, Pyo C S, Cho K H, Lee H S, Yu J H. Deep learning-based stroke disease prediction system using real-time biosignals. ensors. 021; 21(13):4269.

[6] Dev A, Malik S K. Artificial bee colony optimized deep neural network model for handling imbalanced stroke data: ABC-DNN for prediction of stroke. International Journal of E-Health and Medical Communications (IJEHMC). 021;12(5):67-83.

[7] Liu T, Fan W, Wu C. A hybrid machine learning approach to cerebral stroke prediction based on an imbalanced medical dataset. Artificial intelligence in medicine. 019; 101:101723.

[8] Penafiel S, Baloian N, Sanson H, Pino J A. Predicting stroke risk with an interpretable classifier. EEE Access. 020; 9:1154-1166.

[9] Rahman S, Hasan M, Sarkar A K. Prediction of brain stroke using machine learning algorithms and deep neural network techniques. European Journal of Electrical Engineering and Computer Science. 023; 7(1):23-30.

[10] Sailasya, Gangavarapu, Gorli L Aruna Kumari. Analyzing the Performance of Stroke Prediction using ML Classification Algorithms. 2021).

[11] Uppal M, Gupta D, Juneja S, Gadekallu T R, El Bayoumy I, Hussain J, Lee S W. Enhancing accuracy in brain stroke detection: Multi-layer perceptron with Adadelta, RMSProp and AdaMax optimizers. ront. ioeng. Biotechnol. 023; 11:1257591. doi: 10.3389/fbioe.2023.1257591.

[12] Naresh, K.R.P. Applying Discrete Wavelet Transform for ECG Signal Analysis in IOT Health Monitoring Systems. nternational Journal of Information Technology & Computer Engineering, 2022, 10(4), ISSN 2347–3657.

[13] Basava, R.G. AI-powered smart comrade robot for elderly healthcare with an integrated emergency rescue system. World Journal of Advanced Engineering Technology and Sciences, 2021, 02(01), 122–131.

[14] Surendar Rama Sitaraman. Implementing AI Applications in Radiology: Hindering and Facilitating Factors of Convolutional Neural Networks (CNNs) and Variational Autoencoders (VAEs). Journal of Science and Technology, 2022, 7 (10), ISSN:2456-5660.

[15] Chen Y, Chen X, Xu A, et al. A hybrid CNN-Transformer model for ozone concentration prediction. ir Qual Atmos Health. 022; 15(9):1533–1546.

[16] Wu N, Green B, Ben X, et al. Deep transformer models for time series forecasting: the influenza prevalence case. rXiv:200108317. 2020.

[17] Tianyang Lin, Yuxin Wang, Xiangyang Liu, Xipeng Qiu. A survey of transformers, AI Open, 2022; 3:111-132. ttps://doi.org/10.1016/j.aiopen.2022.10.001.

[18] Rodrawangpai B, Daungjaiboon W. Improving text classification with transformers and layer normalization. Machine Learning with Applications. 022; 10:100403.

[19] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I. Attention Is All You Need. Nips), 2017. rXiv preprint arXiv:1706.03762, 2017; 10: p.S0140525X16001837.

[20] Yi Tay, Mostafa Dehghani, Dara Bahri, and Donald Metzler. 2022. Efficient Transformers: A Survey. CM Comput. urv. 55, 6, Article 109 (June 2023), 28 pages. ttps://doi.org/10.1145/3530811.

[21] Junzhe Li, Chenglong Wang, Xiaohan Fang, Kai Yu, Jinye Zhao, Xi Wu, Jibing Gong. Multi-label text classification via hierarchical Transformer-CNN. In Proceedings of the 2022 14th International Conference on Machine Learning and Computing (ICMLC '22); Association for Computing Machinery; New York: NY, USA, 2022 120–125. ttps://doi.org/10.1145/3529836.3529912

[22] https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset

[23] Ushasree D, Praveen Krishna A V, Mallikarjuna Rao C, "Enhanced stroke prediction using stacking methodology (ESPESM) in intelligent sensors for aiding preemptive clinical diagnosis of brain stroke", Measurement: Sensors. 024; 33.

[24] Bhuvanya R, Kavitha M. A real-time e-commerce accessories recommender system by coupling deep learning and histogram features. Intell. uzzy Syst. 2023; 45(1), 1179–1193. https://doi.org/10.3233/JIFS-223754.