Health Guard: Machine Learning Powered Preliminary Diseases Predicto

Health Guard: Machine Learning Powered Preliminary Diseases Predicto

Nisha Wilvicta J 1, Jitendra Prajapati 2, M.A. Qhizar 3, MD Shadab Arshad4, Mohd. Fardeen Shaiekh5

1Nisha Wilvicta J, Computer Science Engineering Department, T John Institute of Technology, Bengaluru

2Jitendra Prajapati, Computer Science Engineering Department, T John Institute of Technology, Bengaluru

3M.A. Qhizar, Computer Science Engineering Department, T John Institute of Technology, Bengaluru

4MD Shadab Arshad, Computer Science Engineering Department, T John Institute of Technology, Bengaluru

5Mohd. Fardeen Shaiekh, Computer Science Engineering Department, T John Institute of Technology, Bengaluru

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract: The evolving landscape of health information-seeking behaviour poses challenges for users navigating online platforms to comprehend diseases, diagnoses, and treatments. Implementing recommendation systems for doctors and medicines through review mining could streamline this process, saving considerable time. However, a significant hurdle lies in users, often laymen, grappling with complex medical vocabulary amidst the vast array of available information. Integrating advanced data mining techniques, particularly in healthcare and biomedicine, contributes to the extraction of valuable insights. Machine learning applications, like disease prediction systems, play a pivotal role in early diagnosis and patient care. In a recent study, machine learning algorithms, including Decision Tree, Random Forest, and Naïve Bayes classifiers, were employed to predict and diagnose diseases, showcasing promising results in enhancing healthcare outcomes.

Keywords: Machine Learning, Data mining, Decision Tree classifier, Random Forest classifier, Naive Bayes classifier, Disease Prediction.