Determinants of Adoption of Mobile Health Applications: A Machine Learning Approach

Abstract

Mobile health (mHealth) application concerns the use of wireless and mobile technologies to support the accomplishment of health objectives. With a doctor’s help, consumers may monitor their health metrics. This is exceptionally focal with the persistent torrent of the unstructured and structured data sets created on periodic intervals from the augmentation of mobile health applications in distinct healthcare systems and products universally. In this study, the leading principle was to examine the impact of perceived usefulness and perceived ease of use on the intentions to adopt Mobile Health application and elucidate with a extensive knowledge of machine learning techniques that might be applied to improve the expertise and knowledge of a mobile health application.12 measurements are based on perceived usefulness in the article, and 8 are based on perceived ease of use. Information was gathered from 200 respondents, of whom 102 used mobile health applications, considered them helpful, and preferred to use them again. The outcomes from the proposed machine learning prototypes have been shown to be quite accurate and effective. A comparison study was conducted based on accuracy values, and the findings indicate that Random Forest and Decision Tree models provide more accuracy than the other models. The research shows that Random Forest and Decision Tree models, which have 100% accuracy rate, produce the most accurate results. Therefore, the study is applicable to forecast accuracy and is valuable. for patients’ readiness to use mHealth applications and can be used to Contact doctors and get health information available at any time and from any location.