Heterogeneous Network-Based Chronic Disease Progression Mining

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....

Full description

Saved in:
Bibliographic Details
Main Authors: Chenfei Sun, Qingzhong Li, Lizhen Cui, Hui Li, Yuliang Shi
Format: Article
Language:English
Published: Tsinghua University Press 2019-03-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2018.9020009
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2096-0654