Abstract
Healthcare insurance fraud has caused billions of dollars in losses in public healthcare funds around the world. In particular, healthcare insurance fraud in chronic diseases is especially rampant. Understanding disease progression can help investigators detect healthcare insurance frauds early on. Existing disease progression methods often ignore complex relations, such as the time-gap and pattern of disease occurrence. They also do not take into account the different medication stages of the same chronic disease, which is of great help when conducting healthcare insurance fraud detection and reducing healthcare costs. In this paper, we propose a heterogeneous network-based chronic disease progression mining method to improve the current understanding on the progression of chronic diseases, including orphan diseases. The method also considers the different medication stages of the same chronic disease. Extensive experiments show that our method can outperform the existing methods by 20% in terms of F-measure.
Highlights
Healthcare insurance fraud has caused billions of dollars in losses in public healthcare funds around the world
We propose a Heterogeneous Network-based Chronic Disease Progression Mining (HNCDPM) method to help us understand the progression of chronic disease, including orphan diseases, detect chronic disease fraud, and reduce healthcare costs
HNCDPM considers the different medication stages of the same disease and obtains two types of rules: the pattern between different periods of different chronic diseases, which indicates the relationship between different types of chronic disease, and the pattern between different stages of the same chronic disease, which shows the clinical path of the chronic disease
Summary
Obtaining chronic disease-related healthcare insurance records, which are defined as a systematic collection of patient healthcare information because of chronic disease, are a major motivation for conducting data-driven healthcare research. To understand chronic disease progression, a considerable amount of work has been done in assessing the risk of developing chronic disease Most of these methods are based on rule-based scoring models which assign scores to various physiological observable factors such as demographic information or family history. These methods provide an intuitive way to assess patients within the short time frame in a specific healthcare setting.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.