Machine learning and the Economics of Preventive Healthcare: Studying cost-benefit analysis of machine learning-driven preventive healthcare measures

Abstract

In this research, the application of machine learning in managing the economic side of preventive health care is examined and an attempt is made to identify and predict those factors in insurance charges that are more important for consideration than the simple arithmetic average. The insurance premium rate prediction relies on a dataset the study obtained from Kaggle, with the machine learning methods used in this study including the following. Thus, the insurance costs are analyzed taking into account age, BMI, smoking status, as well as possible regional differences. To ensure reliable predictive accuracy in the study, Linear Regression,
Random Forest, and eXtreme Gradient Boosting are used. The study also points to age as an influential factor and in this regard, people of advanced ages are most likely to be charged high premiums on insurance. Another category comes out as BMI, which also positively relates to rising insurance costs. Thus, the smoking status can be considered to be the most relevant factor which increases insurance costs 1.5 times as compared with people who do not smoke at all. The findings of this study should be useful to insurance supply chain decision-makers and policymakers interested in improving the efficiency of healthcare cost determination. Therefore, the application of machine learning in the evaluation of healthcare economics for stakeholders entails better risk assessment chances and fair pricing for individuals while possibly encouraging people to live a healthier lifestyle. The outcomes of the presented research highlight the necessity of developing unique approaches to healthcare financing, including the
consideration of disparities in healthcare services accessibility and affordability within specific regions