•  
  •  
 

Abstract

In the wake of disease outbreaks such as COVID-19, real-time health monitoring and prediction systems have become essential for ensuring effective patient care. These systems rely on sensors to monitor biometric parameters such as blood pressure, body temperature, and heart rate, providing continuous and accurate data that medical staff cannot collect manually around the clock. This study presents a robust framework for managing Intensive Care Unit (ICU) patients using Artificial Neural Networks (ANN) with Transfer Learning. The data is analyzed across five distinct time windows, each representing a period of ICU stay based on vital signs and medical test results. Training begins with the first time window, and the acquired knowledge is then transferred to subsequent windows to enhance predictive performance. The proposed system is capable of real-time data analysis from both sensors and medical tests, aiding in the prediction of ICU patient durations. Interim results are stored on a cloud server to enable continuous monitoring of patient conditions. Additionally, the system achieved an impressive prediction accuracy of 97%, further validating its reliability. Moreover, it features an advanced alert mechanism to notify medical teams in the event of sensor malfunctions or abnormal changes in vital signs. These promising outcomes indicate that the developed system is a highly effective tool for ICU patient management, contributing to optimized healthcare operations and a reduced burden on medical staff.

Download

Share

COinS