AI-BASED PREDICTION OF HEART RATE CHANGES FROM BODY TEMPERATURE IN PEDIATRIC INTENSIVE CARE PATIENTS

Abstract

Monitoring vital signs such as heart rate and body temperature is critical for assessing the health condition of children admitted to the Pediatric Intensive Care Unit (PICU). Variations in body temperature often influence heart rate, and abnormal patterns may indicate infections, inflammation, or other medical complications. Early identification of such physiological changes can assist healthcare professionals in making timely clinical decisions and improving patient outcomes. This study proposes an Artificial Intelligence (AI)-based approach to predict heart rate changes based on body temperature data collected from pediatric patients in intensive care settings. The system utilizes machine learning algorithms to analyze large volumes of patient monitoring data and identify patterns between temperature fluctuations and heart rate variations. Historical patient data, including vital sign measurements and clinical observations, are used to train predictive models capable of estimating heart rate responses to temperature changes. The proposed framework involves data preprocessing, feature extraction, model training, and prediction, enabling the system to detect abnormal physiological patterns and support real-time patient monitoring. Machine learning models such as Random Forest, Support Vector Machine, and Neural Networks can be employed to improve prediction accuracy and reliability. The developed system aims to assist clinicians by providing early warning indicators of potential health deterioration, thereby enabling proactive medical intervention. By integrating AI with pediatric healthcare monitoring systems, the proposed approach enhances the efficiency of patient monitoring and contributes to improved decision-making in critical care environments.