Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{207413,
        author = {Tejaswini M and Ambika K B and Sujay S},
        title = {An Intelligent IoT Framework for Predictive Emergency Patient Monitoring and Early Hospital Decision Support},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {1377-1382},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207413},
        abstract = {In today's health care environment, early recognition of patient deterioration prior to hospital arrival is critical to better care preparedness and patient survival. Manual monitoring, delayed communications, paper-based patient assessment methods are the problems traditional emergency triage systems are facing, causing delays in emergency treatment and patient prioritization in critical situations. We present Smart Triage Assistant in Emergency Wards, a healthcare framework that utilizes Internet of Things (IoT) devices and Machine Learning techniques to help monitor patients, predict automated triage and share emergency information prior to patients arriving at hospitals. In the proposed system, patient monitoring is carried out in the transportation of patients using the Internet of Things (IoT) medical sensors like the DS18B20 Temperature Sensor, DHT11 Humidity Sensor, Pulse Sensor, MQ135 CO sensor and ECG Sensor with ESP32 microcontrollers during emergency care. The collected sensor data is sent to the ThingSpeak cloud platform for monitoring and analysis. We have applied classification algorithms such as XGBoost to classify patients as Critical, Moderate and Stable based on patient vital and conditions. The system also includes emergency alert functionalities using SMS alerts and hospital dashboards to help in the better management of emergency response prior to the patient's arrival. It is architected using Node.js and Express.js for backend, centralized healthcare data management with MongoDB, and the monitoring dashboard with React.js. After the experimental assessment on the healthcare dataset, the prediction accuracy obtained by the XGBoost classifier was high, demonstrating the effectiveness of intelligent triage systems in emergency healthcare systems for patient severity classification. The proposed Smart Triage Assistant improves the efficiency of the emergency response, decreases the delay in communicating between ambulance services and hospitals, decreases manual intervention and enhances the safety of the patient by intelligent healthcare monitoring and automatic emergency communicating. Regarding keywords, the project can be divided into different categories such as Smart Triage, Emergency Wards, IoT Healthcare, Machine Learning, ESP32, Real-Time Monitoring, Emergency Alerts, XGBoost, Healthcare Dashboard, and ThingSpeak, and Emergency Response System.},
        keywords = {},
        month = {August},
        }