EFFICIENT PREDICTION OF STROKE PATIENTS USING RANDOM FOREST ALGORITHM IN COMPARISON TO DECISION TREE ALGORITHM

Aim: The study's goal is to use Machine Learning modelling approaches to make an accurate prediction of stroke in patients and to evaluate their performance. Materials and Methods: Random Forest and Decision Tree Algorithms are the two groups employed in this paper. The algorithms were developed and tested on a dataset including over 5000 records of patients' medical and personal information. Through our work 20 iterations were performed for each algorithm. The G-Power test used is about 80%. Results:The results of our research show that Random Forest algorithms have a mean accuracy of 89.56 and Decision Tree algorithms have a mean accuracy of 75.76. p<0.05 is the statistically significant difference between the two methods, as determined by independent t-tests, which is 0.008. Conclusion: The goal of this paper is to use novel ways to improve the efficiency of stroke prediction algorithms and the accuracy of existing systems. The results of the comparison reveal that the Random Forest Algorithm outperforms the Decision Tree Algorithm.