A Variational AutoEncoder-Based Relational Model for Cost-Effective Automatic Medical Fraud Detection

Jie Chen; Xiaonan Hu; Dongyi Yi; Jianqiang Li; Mamoun Alazab

doi:10.1109/TDSC.2022.3187973

A Variational AutoEncoder-Based Relational Model for Cost-Effective Automatic Medical Fraud Detection

Jie Chen, Xiaonan Hu, Dongyi Yi, Jianqiang Li, Mamoun Alazab

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

This work aims to develop a framework of automatic medical fraud detection (AMFD) which can be deployed in healthcare industry. To address the issue that the medical fraud labels are insufficient in both size and classes for training a good AMFD model, this work proposes a novel Variational AutoEncoder-based Relational Model (VAERM) which can simultaneously exploit Patient-Doctor relational network and one-class fraud labels to improve the fraud detection. Then, the proposed VAERM coupled with active learning strategy can assist healthcare industry experts to conduct cost-effective fraud investigation. Finally, we propose an online model updating method to reduce the computation and memory requirement while preserving the predictive performance. The proposed framework is tested in a real world dataset and it empirically outperforms the state-of-the-art methods in both automatic fraud detection and fraud investigation tasks.

Original language	English
Pages (from-to)	3408-3420
Number of pages	13
Journal	IEEE Transactions on Dependable and Secure Computing
Volume	20
Issue number	4
Early online date	Jul 2022
DOIs	https://doi.org/10.1109/TDSC.2022.3187973
Publication status	Published - 1 Jul 2023

Bibliographical note

Funding Information:
This work was supported in part by the National Key R&D Program of China under Grant 2020YFA0908700, in part by the National Nature Science Foundation of China under Grants 62072315, 62073225 and 61836005, in part by the Natural Science Foundation of Guangdong Province-Outstanding Youth Program under Grant 2019B151502018, in part by Guangdong "Pearl River Talent Recruitment Program" under Grant 2019ZT08X603, in part by Shenzhen Science and Technology Program under Grant JCYJ20210324093808021, in part by the Shenzhen Science and Technology Innovation Commission under Grant R2020A045, and in part by the Shenzhen Nanshan People's Hospital of Nanshan District, Shenzhen.

Publisher Copyright:
© 2004-2012 IEEE.

Access to Document

10.1109/TDSC.2022.3187973

Cite this

@article{d7ebca44eab241339e9a4a27128d4eb7,

title = "A Variational AutoEncoder-Based Relational Model for Cost-Effective Automatic Medical Fraud Detection",

abstract = "This work aims to develop a framework of automatic medical fraud detection (AMFD) which can be deployed in healthcare industry. To address the issue that the medical fraud labels are insufficient in both size and classes for training a good AMFD model, this work proposes a novel Variational AutoEncoder-based Relational Model (VAERM) which can simultaneously exploit Patient-Doctor relational network and one-class fraud labels to improve the fraud detection. Then, the proposed VAERM coupled with active learning strategy can assist healthcare industry experts to conduct cost-effective fraud investigation. Finally, we propose an online model updating method to reduce the computation and memory requirement while preserving the predictive performance. The proposed framework is tested in a real world dataset and it empirically outperforms the state-of-the-art methods in both automatic fraud detection and fraud investigation tasks.",

keywords = "Active learning, automatic fraud detection, Computational modeling, Costs, graph convolution network, healthcare industry, Hospitals, Industries, Insurance, Medical diagnostic imaging, one-class learning, Predictive models",

author = "Jie Chen and Xiaonan Hu and Dongyi Yi and Jianqiang Li and Mamoun Alazab",

note = "Funding Information: This work was supported in part by the National Key R&D Program of China under Grant 2020YFA0908700, in part by the National Nature Science Foundation of China under Grants 62072315, 62073225 and 61836005, in part by the Natural Science Foundation of Guangdong Province-Outstanding Youth Program under Grant 2019B151502018, in part by Guangdong {"}Pearl River Talent Recruitment Program{"} under Grant 2019ZT08X603, in part by Shenzhen Science and Technology Program under Grant JCYJ20210324093808021, in part by the Shenzhen Science and Technology Innovation Commission under Grant R2020A045, and in part by the Shenzhen Nanshan People's Hospital of Nanshan District, Shenzhen. Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2023",

month = jul,

day = "1",

doi = "10.1109/TDSC.2022.3187973",

language = "English",

volume = "20",

pages = "3408--3420",

journal = "IEEE Transactions on Dependable and Secure Computing",

issn = "1545-5971",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

number = "4",

}

TY - JOUR

T1 - A Variational AutoEncoder-Based Relational Model for Cost-Effective Automatic Medical Fraud Detection

AU - Chen, Jie

AU - Hu, Xiaonan

AU - Yi, Dongyi

AU - Li, Jianqiang

AU - Alazab, Mamoun

N1 - Funding Information: This work was supported in part by the National Key R&D Program of China under Grant 2020YFA0908700, in part by the National Nature Science Foundation of China under Grants 62072315, 62073225 and 61836005, in part by the Natural Science Foundation of Guangdong Province-Outstanding Youth Program under Grant 2019B151502018, in part by Guangdong "Pearl River Talent Recruitment Program" under Grant 2019ZT08X603, in part by Shenzhen Science and Technology Program under Grant JCYJ20210324093808021, in part by the Shenzhen Science and Technology Innovation Commission under Grant R2020A045, and in part by the Shenzhen Nanshan People's Hospital of Nanshan District, Shenzhen. Publisher Copyright: © 2004-2012 IEEE.

PY - 2023/7/1

Y1 - 2023/7/1

N2 - This work aims to develop a framework of automatic medical fraud detection (AMFD) which can be deployed in healthcare industry. To address the issue that the medical fraud labels are insufficient in both size and classes for training a good AMFD model, this work proposes a novel Variational AutoEncoder-based Relational Model (VAERM) which can simultaneously exploit Patient-Doctor relational network and one-class fraud labels to improve the fraud detection. Then, the proposed VAERM coupled with active learning strategy can assist healthcare industry experts to conduct cost-effective fraud investigation. Finally, we propose an online model updating method to reduce the computation and memory requirement while preserving the predictive performance. The proposed framework is tested in a real world dataset and it empirically outperforms the state-of-the-art methods in both automatic fraud detection and fraud investigation tasks.

AB - This work aims to develop a framework of automatic medical fraud detection (AMFD) which can be deployed in healthcare industry. To address the issue that the medical fraud labels are insufficient in both size and classes for training a good AMFD model, this work proposes a novel Variational AutoEncoder-based Relational Model (VAERM) which can simultaneously exploit Patient-Doctor relational network and one-class fraud labels to improve the fraud detection. Then, the proposed VAERM coupled with active learning strategy can assist healthcare industry experts to conduct cost-effective fraud investigation. Finally, we propose an online model updating method to reduce the computation and memory requirement while preserving the predictive performance. The proposed framework is tested in a real world dataset and it empirically outperforms the state-of-the-art methods in both automatic fraud detection and fraud investigation tasks.

KW - Active learning

KW - automatic fraud detection

KW - Computational modeling

KW - Costs

KW - graph convolution network

KW - healthcare industry

KW - Hospitals

KW - Industries

KW - Insurance

KW - Medical diagnostic imaging

KW - one-class learning

KW - Predictive models

UR - http://www.scopus.com/inward/record.url?scp=85134323470&partnerID=8YFLogxK

U2 - 10.1109/TDSC.2022.3187973

DO - 10.1109/TDSC.2022.3187973

M3 - Article

AN - SCOPUS:85134323470

SN - 1545-5971

VL - 20

SP - 3408

EP - 3420

JO - IEEE Transactions on Dependable and Secure Computing

JF - IEEE Transactions on Dependable and Secure Computing

IS - 4

ER -

A Variational AutoEncoder-Based Relational Model for Cost-Effective Automatic Medical Fraud Detection

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this