1Research Scholar, School of Liberal Arts and Management, P P Savani University, Dhamdod, Kosamba, Surat, 394125, Gujarat, India
Email: ektajain131@gmail.com
ORCID: https://orcid.org/0000-0001-5147-8475
2Professor, School of Liberal Arts and Management, P P Savani University, Dhamdod, Kosamba, Surat, 394125, Gujarat, India
Email: aparnavajpee@gmail.com
ORCID: https://orcid.org/0000-0003-4616-8194
3Research Scholar, School of Liberal Arts and Management, P P Savani University, Dhamdod, Kosamba, Surat, 394125, Gujarat, India
Email: abhilashasahayvarma@gmail.com
ORCID: https://orcid.org/0009-0003-8778-4249
4Research Scholar, School of Liberal Arts and Management, P P Savani University, Dhamdod, Kosamba, Surat, 394125, Gujarat, India
ORCID: https://orcid.org/0009-0009-7020-6817
5Professor, University Institute of Media Studies, Chandigarh University, NH-95, Chandigarh-Ludhiana Highway, Gharuan, Mohali, Punjab - 140413, India
Email: kaushikmishra28@gmail.com
ORCID: https://orcid.org/0000-0003-1396-045X
6Director/Professor: Management/Commerce/International Business, DR G R D College of Science, India
Email: dr.k.k.ramachandran@gmail.com
ORCID: https://orcid.org/0000-0003-0589-4448
Corresponding Author:
Aparna Vajpayee
Professor, School of Liberal Arts and Management, P P Savani University, Dhamdod, Kosamba, Surat, 394125, Gujarat, India
Email: aparnavajpee@gmail.com
ORCID: https://orcid.org/0000-0003-4616-8194
Preventive healthcare and lifestyle intervention is essential in lowering the burden of chronic diseases and the general population health. The study examines the interaction between lifestyle interventions and preventive healthcare models in the lens of social determinants of health. The variables that are targeted in the study include the income level, education, access to healthcare services, physical activity, smoking behavior, and the quality of the diet that affect the involvement of people in the preventive healthcare programs. A dataset of 2000 records of participants in the healthcare was examined in order to establish patterns between lifestyle practices and preventative health outcomes. Prior to the use of machine learning models, the data underwent preprocessing techniques that would guarantee accuracy and reliability in the analysis. The predictive of preventive healthcare participation involved the use of four machine learning algorithms, which were Logistic Regression, Decision Tree, Random Forest and the K-Nearest Neighbors (KNN) algorithms. The performance of the experimental results showed that the Random Forest algorithm performed best in the predictive results with an accuracy of 92, a precision of 0.91, a recall of 0.90, and an F1-score of 0.90. Decision Tree was found to have a higher accuracy of 86% than the Logistic regression with its accuracy standing at 84 percent and the KNN at 83 percent. The analysis of the feature importance revealed that the income level (0.22), education level (0.19) and physical activity (0.18) had the greatest impact on preventive healthcare engagement. The results show how social determinants and lifestyle interventions can be incorporated in preventive medical programs. These types of integrated models can help guide policy makers and medical practitioners to develop better health promotion initiatives and lower the ultimate healthcare expenses.
Keywords: Preventive Healthcare, Lifestyle Interventions, Social Determinants of Health, Machine Learning, Health Behavior Prediction.
How to cite this article: Jain E, Vajpayee A, Varma A, Bokey E, Mishra K, Ramachandran KK. Lifestyle Interventions and Preventive Healthcare Models: A Social Determinants Perspective. Int J Drug Deliv Technol. 2026;16(8s): 268-276; DOI: 10.25258/ijddt.16.8s.38
Source of support: Nil.
Conflict of interest: None