Article Information

Abstract

Many different diseases now affect people due to the state of the environment and lifestyle choices made by humans. Such illnesses must be identified and predicted in advance if they areto reach their terminal phases. Cerebrovascular diseases like stroke are among the top reasons of mortality and these place a heavy financial burden on their victims. Health-related activity is a significant risk factor for stroke and it is receiving a lot of attention in terms of prevention. Numerous machine learning algorithms have been used to predict the occurance of stroke, including predictors such as lifestyle characteristics that allow for automated stroke diagnosis. In order to predict strokes, this study uses five supervised classifiers: K-Nearest Neighbour Algorithm, Decision Tree, Random Forest. Support Vector Machine, and Naïve Bayes. The aforementioned classifiers are trained on the dataset, which consists of 5110 items with 10 characteristics, and their performance is assessed using the confusion matrix. The dataset is pre-processed to make it acceptable for prediction. In the utilised dataset, the Random Forest algorithm performed better than all others in predicting strokes based on several physiological characteristics, with an accuracy of 95.85%. In contrast to an individual's medical history and level of physical activity, machine learning algorithms may be more useful for the clinical estimate of stroke.

Citation Information