Abstract :

The Adaptable Critical Patient Caring System Addresses The Urgent Need For Efficient Healthcare Management In Developing Countries Such As Bangladesh, Where Most Hospitals Lack Scalable And Intelligent Systems For Serving Critical Patients. This Project Aims To Design An Effective Real-time Feedback System To Assist Healthcare Professionals In Continuously Monitoring And Managing Patients With Severe Conditions.This Study Proposes A Generic Architecture, Associated Terminology, And A Classificatory Model That Integrates Machine Learning (ML) With IBM Cloud Computing, Utilized As Platform As A Service (PaaS). IBM Watson Studio Serves As The Environment For Data Storage, Model Training, And Deployment. Several ML Algorithms, Including Naïve Bayes, Logistic Regression, K-Nearest Neighbors, Decision Tree, Random Forest, Gradient Boosting, And Multilayer Perceptron (MLP) Classifiers, Are Implemented As Base Predictors. To Improve Prediction Accuracy, Ensemble Learning With The Bagging Technique Is Applied Using Bagging Random Forest, Bagging Extra Trees, Bagging KNeighbors, Bagging SVC, And Bagging Ridge.A Mobile Application, Critical Patient Management System (CPMS), Has Been Developed To Visualize And Access Real-time Patient Data. The Architecture Enables Dynamic Model Training And Deployment By Retrieving Data From IBM Cloud At Periodic Intervals..By Combining ML Models With A Mobile Interface, The Proposed System Provides A Scalable, Intelligent, And Real-time Healthcare Solution To Enhance Critical Patient Management And Hospital Efficiency. Index Terms:-Machine Learning (ML), Predictive Healthcare, IBM Cloud, Ensemble Learning, Real-Time Monitoring, Critical Patient Management System (CPMS), Cloud Computing, Smart Healthcare.

Published:

29-10-2025

Issue:

Vol. 25 No. 10 (2025)

Page Nos:

398-406

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite