Disease Prediction: Smart Disease Prediction System using Random Forest Algorithm

• Published in: 2021 IEEE International Conference on Intelligent Systems, Smart and Green Technologies (ICISSGT) pp. 48 - 51
• Main Authors: Swarupa, A.N.V.K, Sree, V.Hema, Nookambika, S., Kishore, Y. Kiran Sai, Teja, U. Ravi
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-11-2021
• Subjects: disease prediction; Forestry; Intelligent systems; Machine learning algorithms; Medical diagnosis; Prediction algorithms; random forest; Random forests; Task analysis
• DOI: 10.1109/ICISSGT52025.2021.00021

People nowadays suffer from a variety of diseases as a result of their living habits and the state of the environment. As a result, predicting sickness at an early stage becomes a crucial task. A doctor's ability to establish accurate diagnosis solely on symptoms, on the other hand, is restricted. For the prevention and treatment of illness, an accurate and timely examination of any health-related problem is critical and challenging. In the case of a critical illness, the conventional method of diagnosis may not be adequate. There will be a huge requirement for Automated Disease Prediction System that will reduce these challenges. Developing a medical diagnosis system based on the Random Forest machine learning algorithm for disease prediction can aid in a more accurate diagnosis than the conventional way. The goal of constructing a classification system using a machine learning algorithm i.e Random Forest will substantially enable physicians in anticipating and detecting diseases at an early stage, greatly assisting in the resolution of health-related issues. For the analysis, a sample of 4920 patient records with 41 disorders was chosen. A total of 41 diseases made up the dependent variable. We enhanced 95 of the 132 independent variables (symptoms) that are closely related to illnesses. This paper illustrates a disease prediction system constructed using the Random Forest Machine Learning algorithm. Experiments were conducted with a standard symptoms dataset, and this model achieved 95 % classification accuracy. Machine learning and the Python programming language with the Tkinter Interface were used to create this disease prediction using Random Forest.