A Review of Methods Used for Health Prediction and Monitoring Utilizing Electronic Medical Records (EMR) System

Abstract

With the global population steadily increasing, there is a growing demand for electronic medical records due to the substantial amount of information generated within hospitals. Handling these records physically can prove challenging. Electronic medical records (EMRs) have had a profound impact on the healthcare sector by digitizing hospital records, thereby enhancing patient care. By enabling electronic entry, maintenance, and storage of medical data over extended periods, EMRs contribute to improved patient care and safety. This review examines and compares various methods and techniques aimed at diagnosing and predicting diseases accurately through the use of EMRs. Additionally, it presents a comparative analysis of different approaches available for health prediction. Recent publications were studied to categorize these techniques into Deep Learning (DL) Methods, Machine Learning (ML) Methods, and Rule-Based Methods. Moreover, the review outlines the advantages and disadvantages associated with these diverse techniques and discusses their impact on the healthcare industry.