Developing a Pre-Consultation System using Machine Learning for Medical Diagnostics

Abstract

Due to their lifestyle choices and environment, people nowadays suffer from a broad variety of ailments. Therefore, it becomes crucial to explore the potential for earlier disease prediction. However, doctors find it impossible to accurately forecast based solely on symptoms. The most difficult challenge is making an accurate disease forecast. Machine learning is crucial in disease prediction to address this problem. In the area of medicine, there is a huge data increase each year. As a result of the expansion of data in the medical and healthcare sectors, reliable analysis of medical data—which benefited from early patient care—has grown. Machine learning algorithms can discover possibilities in the provided medical dataset with the use of disease data. The main objective of this study is detecting the probable disease with high accuracy and challenges are data quality & quantity and high dimensionality. This study has suggested a broad possibility of disease occurrence based on the symptoms of the patient. Decision Tree, Random Forest, K-Nearest Neighbor (KNN), and Naive Bayes algorithms are used to accurately forecast diseases. A collection of disease symptoms is necessary for disease prediction.The accuracy of the prediction is the main challenge which depends on the quality and quantity of the data used to train the model. Medical data can be incomplete, biased, or inconsistent, which can affect the performance of the model. So our goal is to develop the correct accuracy prediction model.