Predictive Protection of Heterogeneous Sensitive Data

Abstract

It will be necessary to deal with medically sensitive data that is also diverse, that is, it will comprise a wide variety of different data types and formats, in order to achieve the objectives of this study. It is possible that they are unclear and of low quality as a consequence of issues such as missing numbers, excessive data duplication, and untruthfulness, among other issues. For the purpose of meeting the increasing demand for corporate information, it is vital to bring together a diverse range of information sources in a one location. A realistic prediction of lung disease may be made based on information provided by the patient, such as the number of cigarettes smoked each day or any other significant component of the patient's health. The figure below serves as an indication of how we may make use of sensitive data while remaining diverse, and how we can do so in a safe and secure environment. Also included is a study and comparison of the machine learning methodologies used by Bayesian and random forest classification and regression, as well as regression and classification using Bayesian and random forest classification and regression. Additionally, regression and classification using Bayesian and random forest classification and regression are included.