yashshah2002 / disease_prediction_system_ml

Abstract One of the fastest-growing fields is the health care industry. The medical industries have a huge amount of data set collections about patient details, diagnosis, and medications. To turn these data into useful patterns and to predict coming up trends data mining approaches are used in healthcare industries. This project explores different data mining techniques which are used in the medical field for good decision making. Proposed Work This project will be used to predict disease according to the symptoms entered by the user. The application when operated will display a GUI (Graphical User Interface made with Tkinter) that will ask the user to enter a minimum of 3 symptoms. Furthermore, for a user-friendly experience, an autocomplete function will assist the user in selecting the symptoms easily. Post entering the symptoms, the trained model will use a decision tree classifier, naive bayes classifier, and random forest classifier individually for the prediction of diseases and the final results will be displayed on the GUI.

Abstract

One of the fastest-growing fields is the health care industry. The medical industries have a huge amount of data set collections about patient details, diagnosis, and medications. To turn these data into useful patterns and to predict coming up trends data mining approaches are used in healthcare industries. This project explores different data mining techniques which are used in the medical field for good decision making.

Proposed Work

This project will be used to predict disease according to the symptoms entered by the user. The application when operated will display a GUI (Graphical User Interface made with Tkinter) that will ask the user to enter a minimum of 3 symptoms. Furthermore, for a user-friendly experience, an autocomplete function will assist the user in selecting the symptoms easily. Post entering the symptoms, the trained model will use a decision tree classifier, naive bayes classifier, and random forest classifier individually for the prediction of diseases and the final results will be displayed on the GUI.