Multiple Disease Prediction Using Machine Learning Algorithm (XGBoost Algorithm)

Abstract

Every day, many individuals encounter different illnesses. The prognosis of a disease is the most pivotal part of treatment. The enormous increase in healthcare and medical data has enabled accurate medical data analysis, which aids in early sickness discovery and proactive patient care. This study focuses on analyzing extensive medical data by employing supervised classification algorithms, with a primary focus on the XGBoost (Extreme Gradient Boosting) Classifier. The proposed model anticipates the most probable disease based on symptoms and predicts the likelihood of whether a person might be suffering from a particular illness. XGBoost is known for its high performance, scalability, and ability to handle imbalanced and sparse data, making it well-suited for complex healthcare datasets. By combining predictions with XGBoost as the core model, the system achieves improved diagnostic accuracy and reduced false positives compared to traditional individual models. This study enhances the swiftness of clinical decision-making and assists healthcare organizations in providing timely and precise early patient care. It also supports medical professionals in formulating more effective patient treatment strategies.