Prediction System for Symptoms Driven Disease Diagnosis

Healthcare matters most to human beings. Due to the advancements in technology, people have become quite impatient in developing solutions for any problem they encounter. Since the amount and diversity of healthcare data including the speed at which it is generated has grown significantly in recent years, it necessitates the development of effective machine learning tools to enable accurate prediction of potential diseases. Using such techniques, this study presents a systematic method for detecting human diseases based on symptoms. This study compares the effectiveness of machine learning methods such as Logistic Regression, Decision Trees, Random Forest Classifier, Support Vector Machines, Naïve Bayes, and Artificial Neural Networks (ANN) in predicting diseases based on input symptoms. Furthermore, the research sheds light on the development of a multi-disease prediction system that not only identifies probable diseases but also provides patients with preventative actions and recommendations. The study also aims to contribute to improve the constraints of previous researches on disease prediction systems, ultimately improving healthcare outcomes for people globally.