A Robust Multi-Class Classification Model for Pharma Healthcare Data Using Artificial Intelligence TechniquesMr. Anoop Sunarty,

Abstract

Artificial Intelligence (AI) is rapidly becoming an integral part of healthcare systems across the globe. This is because AI can process large volumes of medical data and make more informed clinical decisions. In the healthcare sector, machine learning and deep learning algorithms are used in various applications, such as intelligent diagnostic systems, medical image analysis, pharmaceutical data processing, and illness prediction. This study presents a MIMIC-IV Dataset based Smart Classification Model for Pharma Healthcare Data. Different datasets preprocessing techniques have been used in the experimental analysis in order to improve the data quality and model performance. These methods comprised missing value imputation, normalization, one-hot encoding, outlier removal and data balancing using SMOTE. XGBoost achieved an impressive 96% accuracy (ACC), 94.6% precision (PRE), 91.6% recall (REC), and 97.7% F1-score (F1) out of all the models used. The outcomes of the proposed classification model based on XGBoost are reliable, accurate and efficient and looks extremely suitable for smart systems in the healthcare and medicine field as well as advanced systems in clinical decision making.