Abstract—Stroke is a medical condition that occurs when there is any blockage or bleeding of the blood vessels either interrupts or reduces the supply of blood to the brain resulting in brain cells starting to die. It causes the disability of multiple organs or unexpected death. The time of cure in stroke patients relies on symptoms and injury of organs. The stroke is avoided in up to 80 percent of cases if the patients identify and relieve the dangers in due time. With the advancement of machine learning in medical imaging, the early recognition of stroke is very much possible that plays a vital role in diagnosis and getting read of this life-taking disease. Considering the above case, in this paper, we have proposed a Convolutional Neural Network (CNN) model as a solution that predicts the probability of stroke of a patient in an early stage to achieve the highest efficiency and accuracy. The model is an improvised variant of a multi-layer perceptron and it comprises info, a yield layer, and many secret layers. The data set used in the prediction model is the health care data set which has eleven features and only one target class as the outcome. Therefore, we have also applied some feature selection methods for extracting the most contributed features in the classification. The model accuracy is compared with other machine learning models and found the model is better than others with an accuracy of 95.5 percent.  
 

Index Terms—stroke prediction, machine learning approach, data mining, neural network, CNN 
 

Cite: Md. Ashrafuzzaman, Suman Saha, and Kamruddin Nur, "Prediction of Stroke Disease Using Deep CNN Based Approach," Journal of Advances in Information Technology, Vol. 13, No. 6, pp. 604-613, December 2022.

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.