Citation :

Mitali Hemant Chaudhari, Nisha Wandile Kimmatkar, Girija A. Deshpande, Rutuja Gangadhar Khedkar, "Enriching Brain Stroke Detection through A Hybrid Data Model," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 1, pp. 128-141, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I1P110

Abstract

The leading cause of brain stroke is the sudden blocking of blood flow to the brain through a blood vessel or due to damage to a blood vessel in the brain. More often, this brain stroke is the result of long-standing diseases that occur due to some evil habits of patients. These diseases are often measured as high blood pressure, diabetes, high cholesterol, smoking, and a sedentary lifestyle. Many deep learning models exist to detect the possibilities of brain stroke by considering the disease parameters. But only finger-counting techniques are available, which eventually consider the lifestyle of the people to predict the impact of a brain stroke. Hence, a multi-data hybrid model is required to evaluate the possibilities of causing a brain stroke by using the imagery dataset and statistical dataset. The proposed model initially trains the imagery brain stroke dataset using the channel boost convolutional neural network after boosting the channels to an absolute grayscale factor. On the other hand, the proposed model considers the statistical dataset for training using the LSTM model. Finally, the input image and the statistical data from the user are subjected to non-negative matrix factorization to obtain the results of brain stroke predictions. The obtained results are evaluated by the confusion matrix, which yields almost 98.12% accuracy, indicating the quality of our model.

Keywords

Brain Stroke Detection, Deep learning, Convolution Neural Network, Long Short-Term Memory (LSTM), Hybrid Neural Network.

References

[1] Tomonobu Kodama et al., “Ischemic Stroke Detection by Analyzing Heart Rate Variability in Rat Middle Cerebral Artery Occlusion Model,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 26, no. 6, pp 1152-1160, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Zhong Zhang et al., “Deep Contextual Stroke Pooling for Scene Character Recognition,” IEEE Access, vol. 6, pp. 16454-16463, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Ying Xuan Zhi et al., “Automatic Detection of Compensation During Robotic Stroke Rehabilitation Therapy,” IEEE Journal of Translational Engineering in Health and Medicine, vol. 6, pp. 1-7, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Zhengmi Tang et al., “Stroke-based Scene Text Erasing using Synthetic data for Training,” IEEE Transactions on Image Processing, vol. 30, pp. 9306-9320, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Quang-Vinh Dang, and Guee-Sang Lee, “Document Image Binarization with Stroke Boundary Feature Guided Network,” IEEE Access, vol. 9, pp. 36924-36936, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Fu-Cheng Wang et al., “Real-Time Detection of Gait Events by Recurrent Neural Networks,” IEEE Access, vol. 9, pp. 134849-134857, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Shir Kashi et al., “A Machine-Learning Model for Automatic Detection of Movement Compensations in Stroke Patients,” IEEE Transactions on Emerging Topics in Computing, vol. 9, no. 3, pp. 1234-1247, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Thapanan Janyalikit, and Chotirat Ann Ratanamahatana, “Time Series Shapelet-based Movement Intention Detection Toward Asynchronous BCI for Stroke Rehabilitation,” IEEE Access, vol. 10, pp. 41693-41707, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Jaehak Yu, “AI-based Stroke Disease Prediction System using ECG and PPG Bio-Signals,” IEEE Access, vol. 10, pp. 43623-43638, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Chenzhe Li et al., “Deep-Learning-Enabled Microwave-Induced Thermoacoustic Tomography based on ResAttU-Net for Transcranial Brain Hemorrhage Detection,” IEEE Transactions on Biomedical Engineering, vol. 70, no. 8, pp. 2350-2361, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Muhammad Asim Saleem et al., “Innovations in Stroke Identification: A Machine Learning-based Diagnostic Model using Neuroimages,” IEEE Access, vol. 12, pp. 35754-35764, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Chi-Huang Shih et al., “A Post-Stroke Rehabilitation System with Compensatory Movement Detection using Virtual Reality and Electroencephalogram Technologies,” IEEE Access, vol. 12, pp. 61418-61432, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[13] S.M. Mahim et al., “TransMixer-AF: Advanced Real-Time Detection of Atrial Fibrillation Utilizing Single-Lead Electrocardiogram Signals,” IEEE Access, vol. 12, pp. 143149-143162, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Muhammad Usama Tanveer et al., “Neuro-VGNB: Transfer Learning based Approach for Detecting Brain Stroke,” IEEE Access, vol. 12, pp. 178862-178874, 2024.
[CrossRef] [Google Scholar] [Publisher Link]