Comparative Analysis of Customised Neural Network Model and ML Classifiers for Brain Stroke Prediction

An abrupt interruption of the brain's blood supply leads to stroke, which causes severe damage to the brain. Due to this condition, there are people disabled and thus leading to death. In this work, the dataset contains ten features where environmental tests are done for the stroke which is utilized to evaluate the efficiency of Machine Learning classifiers and Deep Learning Artificial Neural Network. The purpose of this paper is to provide a forecast of the likelihood of a brain stroke occurring at an early stage using Machine Learning and Deep Learning techniques. The accuracy and efficiency of various types of Machine Learning models and customized Deep Learning models have been compared based on this impression. The custom Deep Learning model here used is an Artificial Neural Network with dropouts having the highest accuracy of 97.06% using RMSprop optimizer and a Decision Tree Machine Learning Classifier, achieved the highest accuracy of 95.98%.