AN INTELLIGENT DISEASE PREDICTION AND DRUG RECOMMENDATION PROTOTYPE BY USING MULTIPLE APPROACHES OF MACHINE LEARNING ALGORITHMS

Abstract

Numerous people suffer from various illnesses on a daily basis. The most important aspect of treatment is determining a disease's prognosis. Accurate medical data analysis has been made possible by the massive growth in healthcare and medical data, which supports proactive patient care and early illness detection. The XGBoost (Extreme Gradient Boosting) Classifier is the main topic of this work, which uses supervised classification methods to analyse large amounts of medical data. The suggested model predicts the possibility that a person may be afflicted with a specific sickness and forecasts the most likely disease based on symptoms. Complex healthcare datasets are a good fit for XGBoost because of its high performance, scalability, and capacity to handle skewed and sparse data. Compared to conventional individual models, the system provides better diagnostic accuracy and fewer false positives by integrating predictions using XGBoost as the main model. This research improves clinical decision-making speed and helps healthcare organisations deliver accurate and timely early patient treatment. Additionally, it aids healthcare providers in creating more efficient patient care plans