Patients’ Health Analysis using Machine Learning

Abstract

Examining patient health through the lens of Machine Learning (ML) was the primary objective of this research. We accomplished this by using the auto-ML-Pycaret and Extreme Gradient Boost (XGBoost) classifiers. This article details the three-step process we used to construct the XGBoost model: data analysis, feature engineering, and model development. Data science tools like Google Colab (GC) and the Jupyter notebook were used for these assignments. Our next topic is the auto-ML-Pycaret model, a powerful instrument for ML applications. At last, we compare the two models' performance according to their accuracy levels. We got 88% accuracy with the auto ML Pycaret model, whereas the initial ML model was 87% accurate. When comparing the XGBoost and auto-ML Pycaret models, we found that the latter had superior performance in terms of accuracy percentages and time factor.