IRO Journals
Journal of Ubiquitous Computing and Communication Technologies

Explainable Random Forest Framework for Multi-Class Lifestyle Disease Risk Prediction Using BRFSS Data

Open Access
Published: 17 October, 2026
Pages: 357-368
  • Prema P. , Prema P.
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
  • Nivetha P. , Nivetha P.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
  • Nagasakthi N. Nagasakthi N.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Dindigul, India
view PDF
view PDF

How to Cite

P., Prema, Nivetha P., and Nagasakthi N. 2026. “Explainable Random Forest Framework for Multi-Class Lifestyle Disease Risk Prediction Using BRFSS Data”. Journal of Ubiquitous Computing and Communication Technologies 8 (4): 357-68. https://doi.org/10.36548/jucct.2026.4.004.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Explainable Machine Learning
Lifestyle Disease Risk Prediction
Health Behaviour Analysis
Ensemble Classification
Synthetic Data Balancing
Feature Importance Analysis
Preventive Recommendation Generation

Abstract

With the increase in lifestyle diseases globally, there is a need for an effective machine learning approach to predict people who are at risk. In this research, a machine learning framework for multiclass prediction of risk of lifestyle disease using the BRFSS 2024 dataset is developed. There are six risk groups: Healthy, Diabetes Risk, Hypertension Risk, Obesity Risk, Heart Disease Risk, and Kidney Disease Risk. Data preprocessing in the proposed framework is done by treating missing values, converting categorical variables into numeric variables, eliminating duplicate and inconsistent entries, normalizing using the Z-score method, and correlation-based feature selection. Synthetic Minority Over-sampling Technique (SMOTE) is implemented to solve the problem of class imbalance. There are five classifiers tested using the 80/20 ratio for training and testing. They include Logistic Regression, SVM, KNN, Decision Tree, and Random Forest. The analysis reveals that the Random Forest performs well with an accuracy rate of 94.8%, and thus, is selected as the final model for predicting the diseases. Age, smoking, and sleep time have also been identified as important features using feature importance analysis that play an important role in predicting the risk of developing lifestyle diseases.

References

  1. World Health Organization. Noncommunicable diseases progress monitor. World Health Organization, 2025.
  2. Mensah, George A., Gregory A. Roth, and Valentin Fuster. ”The global burden of cardiovascular diseases and risk factors: 2020 and beyond.” Journal of the American college of cardiology, 2019, vol. 74, no. 20: 2529-2532.
  3. Ke, Guolin, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. ”Lightgbm: A highly efficient gradient boosting decision tree.” Advances in Neural Information Processing Systems, 2017, vol. 30.
  4. Uddin, Shahadat, Arif Khan, Md Ekramul Hossain, and Mohammad Ali Moni. ”Comparing different supervised machine learning algorithms for disease prediction.” BMC Medical Informatics and Decision Making, 2019, vol. 19, no. 1: 281.
  5. Battineni, Gopi, Getu Gamo Sagaro, Nalini Chinatalapudi, and Francesco Amenta. ”Applications of machine learning predictive models in the chronic disease diagnosis.” Journal of Personalized Medicine, 2020, vol. 10, no. 2: 21.
  6. Akiba, Takuya, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. ”Optuna: A next-generation hyperparameter optimization framework.” In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, 2623-2631.
  7. Hossain, Khondoker Murad, and Tim Oates. ”Ten-Guard: tensor decomposition for backdoor attack detection in deep neural networks.” arXiv preprint, 2024, arXiv:2401.05432.
  8. Sumalatha, P., M. Akanksha, and Maria Fatima. ”Lifestyle Disease Prediction.” International Journal of Scientific Research in Science, Engineering and Technology, 2023, vol. 10, no. 3: 39-42.
  9. Arumugam, K., Mohd Naved, Priyanka P. Shinde, Orlando Leiva-Chauca, Antonio Huaman-Osorio, and Tatiana Gonzales-Yanac. ”Multiple disease prediction using Machine learning algorithms.” Materials Today: Proceedings, 2023, vol. 80: 3682-3685.
  10. Tiwari, Achyut, Aryan Chugh, and Aman Sharma. ”Ensemble framework for cardiovascular disease prediction.” Computers in Biology and Medicine, 2022, vol. 146: 105624.
  11. Centers for Disease Control and Prevention, Behavioral Risk Factor Surveillance System (BRFSS): 2024 Survey Data and Documentation, Available: https://www.cdc.gov/brfss/annual_data/annual_2024.html