부산대학교 도서관

The objective of this study is to develop a machine learning model (ML) to obtain the risk of stroke in patients. We used a dataset of 4,981 patients to train and test the model. Decision Tree Classifier (DTC) was used as the ML model, which is a widely used algorithm for classification problems. Before training the model, we cleaned the dataset by removing inaccurate and incomplete data to ensure that the model is not fed with faulty data. This confirms that the model can make accurate predictions based on the available data. After cleaning the data, we trained the DTC model and tested it on the same dataset. Our model performance shows that this model can accurately predict the risk of stroke in patients with high accuracy. The outcome of this study can be beneficial for both patients and medical professionals. Patients can be informed of their risk of stroke and can take preventative measures to reduce their risk. In conclusion, we successfully developed an ML model using a Decision Tree Classifier to obtain the risk of stroke in patients. Our study demonstrates the potential of ML in healthcare and its application in predicting the occurrence of diseases. This article can serve as a foundation for future research on improving the accuracy of stroke risk prediction models, which can lead to better patient outcomes and improved healthcare practices.