Stroke is a condition that occurs when blood supply to the brain is
disrupted or reduced due to rupture of blood vessels. Stroke ranks second as a
non-communicable disease that causes death. The purpose of this study is to
classify stroke and measure the level of accuracy, precision, recall and f1-score
using the support vectors machine method and genetic algorithms as optimization.
SVM is an algorithm that is often used for classifying a model. Genetic algorithms
are used to perform computer simulations to get the best solution based on the
visible candidate solutions. Classification performance using SVM results
obtained an accuracy of 94%. The SVM-GA method produces an accuracy of
94%. This proves that the SVM classification using GA optimization with the data
used in the study produces the most optimal accuracy of 94%.