Advances in technology have now developed into various fields, one of which is the health sector. With the support of this technology, it can help the work of health workers in dealing with their patients. Not only acting as a curative and rehabilitative, but technology can also be used as a preventive medium for dangerous diseases; an example is a stroke. According to the World Health Organization (WHO), stroke is the second leading cause of death and the third leading cause of disability. Stroke can occur due to lifestyle factors (such as tobacco and alcohol use) and medical factors (such as a history of heart disease and hypertension). Data on patients who have factors that trigger stroke can be used to detect and predict the potential for the patient to have a stroke or not. The research was conducted using a Deep Learning algorithm, namely Convolutional Neural Network (CNN), to train the data to produce an architecture that can predict the possibility of brain stroke. The dataset used in this study was obtained from the Brain Stroke Detection public domain dataset, which has 11 attributes (including gender, age, hypertension, heart disease, ever married, work type, residence type, average glucose level, BMI, smoking status, and stroke). The architecture produced an excellent accuracy of 98%, an F1-Score of 98%, and a Loss of 0.1180. Besides, this architecture has a good fitting, which shows that the architecture made is robust enough to predict the potential for the occurrence of brain stroke.