International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 07 | Jul 2025
p-ISSN: 2395-0072
www.irjet.net
E Nurse – Student Health Risk Analysis and Personalized Evidencebased Diet Recommendation System with Machine Learning Techniques Kavitha H C1, H.P. Mohan Kumar2 1Department of MCA, P.E.S. College of Engineering, Mandya, Karnataka, India 2Department of CS&E, P.E.S. College of Engineering, Mandya, Karnataka, India
---------------------------------------------------------------------***--------------------------------------------------------------------explore how effectively students cope with their academic Abstract - The shift in lifestyle among today’s youth,
journey and identify the challenges they face. Insights gained from this analysis enable educators to recognize each student’s learning style and determine the most effective teaching strategies.
particularly college students, has led to a noticeable increase in health issues. Lack of physical activity, irregular routines, and frequent consumption of fast food contribute to unbalanced body weight and poor overall health. One of the key indicators of health is Body Mass Index (BMI), which is used to classify individuals into categories such as underweight, normal weight, overweight, and obese based on their height and weight. Being underweight may result in malnutrition, lack of essential vitamins, poor immunity, and developmental delays. On the other hand, excess weight is often linked to serious conditions like Type-2 diabetes. To detect and prevent these issues early, machine learning (ML) can be used to create predictive health models. This project presents a smart application called E-Nurse, which functions like a digital nurse in colleges. It uses machine learning algorithms such as Naive Bayes, Decision Tree, and Random Forest to analyze student health data. These algorithms are evaluated to find the most accurate model for predicting health risks. The system considers multiple factors including age, gender, food habits, academic pressure, family background, BMI, height, and weight to assess both physical and mental health issues. Based on the results, it suggests personalized and evidence-based diet recommendations to promote better student health. Developed using Microsoft tools like Visual Studio and SQL Server, this system aims to support students and educational institutions by providing timely health insights and tailored dietary guidance.
To accomplish this, machine learning algorithms such as Naive Bayes, Random Forest, and Decision Tree are applied to educational datasets. These models evaluate various attributes including age, gender, eating habits, family environment, mental stress, academic scores, height, weight, and BMI to detect possible health-related issues. The predictive accuracy of each model is compared to determine the most effective approach. The project includes the development of a user-friendly software application that utilizes these trained models to identify potential health risks among students. By diagnosing issues early, the system supports educators and health professionals in taking proactive steps to assist students. This results in improved academic outcomes through timely intervention and personalized support. This intelligent system is an innovative step toward integrating health analysis into academic monitoring, ensuring a holistic approach to student success [6].
2. RELATED WORK [1] In a foundational study, the World Health Organization (2019) developed evidence-based nutrition guidelines rooted in clinical trials and scientific research. These guidelines help individuals make healthier food choices and assist professionals in creating nutrition plans. Although the study emphasized dietary assessment techniques, it did not explore AI-driven personalization.
Key Words: Data science, Naive Bayes, SVM, Random Forest, GUI, Student, Mental Issues, Machine learning, fertilizer.
1. INTRODUCTION Educational institutions strive to ensure maximum academic success for all students. However, academic performance is often affected by several factors including gender, communication ability, memory capacity, health conditions, family background, and participation in extracurricular activities. Understanding these influences early can help in addressing issues before they impact a student’s performance. Often, students struggle with learning, especially in the early stages of a course. This project aims to
© 2025, IRJET
|
Impact Factor value: 8.315
[2] Smith and Doe (2020) investigated the use of Artificial Intelligence (AI) for generating personalized diet plans based on individual health profiles and dietary preferences. They employed deep learning and natural language processing (NLP) to process nutritional datasets and produce optimized meal suggestions, improving dietary adherence and health outcomes.
|
ISO 9001:2008 Certified Journal
|
Page 842