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{192071,
        author = {Shivaprasad Satla},
        title = {An AI-Driven Approach for Obesity Prediction Using Deep Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {252-260},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192071},
        abstract = {Obesity has become a major global public health issue due to its strong association with chronic conditions such as diabetes, cardiovascular disease, and hypertension. Early prediction of obesity risk is essential to enable preventive healthcare and support personalized lifestyle interventions. This work proposes DeepHealthNet, an intelligent obesity prediction framework that utilizes machine learning and deep learning techniques to classify individuals into obesity categories using demographic, lifestyle, and physiological parameters. The system analyzes key features such as age, gender, height, weight, body mass index (BMI), dietary habits, and physical activity levels. To enhance predictive reliability, data preprocessing steps including missing value handling, normalization, and feature selection are applied. Multiple supervised models including Random Forest, Support Vector Machine, Gradient Boosting, and deep neural networks are evaluated using standard performance metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. Experimental results show that DeepHealthNet achieves superior performance compared to conventional baseline models, demonstrating its effectiveness in capturing complex patterns within structured health data. The framework also supports interpretability through feature importance analysis, enabling better understanding of contributing factors behind obesity risk. Due to its scalability and adaptability, DeepHealthNet can be integrated into digital health platforms, mobile health applications, and clinical decision-support systems for continuous monitoring and early risk alerts. Overall, the proposed system highlights the potential of deep learning–driven predictive analytics in improving obesity risk assessment and strengthening preventive healthcare strategies.},
        keywords = {Obesity Prediction, Deep Learning, Machine Learning, Artificial Neural Network, Health Data Analysis, Lifestyle Factors, Body Mass Index (BMI).},
        month = {January},
        }