Optimizing Healthcare Management Systems with AI and Machine Learning

Abstract

This paper explores the optimization of healthcare management systems using Artificial Intelligence (AI) and Machine Learning (ML). As the complexity of healthcare systems continues to grow, AI and ML have emerged as key tools to improve decision-making, resource allocation, and patient care. This paper provides a detailed discussion on four AI algorithms, namely Logistic Regression, Random Forest, Support Vector Machine (SVM), and Neural Networks, and their application in the prediction of patient outcomes, including postoperative LOS and disease diagnosis. Experimental results indicate that the accuracy of the Neural Network model was 91.5%, outperforming other algorithms. The precision of the Random Forest model was 87.3%, while the recall of SVM was 82.4%. Apart from the above point, the current research has noted AI application use for the reduction of healthcare-related cost optimization via predicting financial risk and improving a management strategy pertaining to patient data. Machine learning implementation in an edge computing facility showcased a drop in patient wait time by up to 20% and achieved 15% increase in overall efficiency. Promising results and huge challenges exist side by side with model interpretation and data protection issues. This study highlights the requirement for future AI transparency and ethical data management in order to achieve the full potential of AI in healthcare.