Graph Analysis for Detecting Fraud, Waste, and Abuse in Healthcare Data

@inproceedings{Liu2016GraphAF,
  title={Graph Analysis for Detecting Fraud, Waste, and Abuse in Healthcare Data},
  author={Juan Liu and Eric A. Bier and Aaron Wilson and John Alexis Guerra G{\'o}mez and Tomonori Honda and Kumar Sricharan and Leilani Gilpin and Daniel Davies},
  booktitle={AI Mag.},
  year={2016}
}
Detection of fraud, waste, and abuse (FWA) is an important yet difficult problem. In this paper, we describe a system to detect suspicious activities in large healthcare claims datasets. Each healthcare dataset is viewed as a heterogeneous network of patients, doctors, pharmacies, and other entities. These networks can be large, with millions of patients, hundreds of thousands of doctors, and tens of thousands of pharmacies, for example. Graph analysis techniques are developed to find… 

Figures from this paper

Graph analytics for healthcare fraud risk estimation

TLDR
A novel approach to estimating healthcare fraud (HCF) risk that applies network algorithms to graphs derived from open source datasets that calculates behavioral similarity to known fraudulent and non-fraudulent healthcare providers with respect to measurable healthcare activities.

A META-ANALYSIS OF FRAUD , WASTE AND ABUSE DETECTION METHODS IN HEALTHCARE

TLDR
This study examines and analyzes fraud, waste and abuse detection methods used in healthcare to reveal the strengths and limitations of each approach and revealed that fraud detection methods are difficult to implement in the healthcare system.

A Sequence Mining-Based Novel Architecture for Detecting Fraudulent Transactions in Healthcare Systems

TLDR
A novel process-based fraud detection methodology to detect insurance claim-related frauds in the healthcare system using sequence mining concepts is presented and validated using last five years of a local hospital’s transactional data that includes many reported cases of fraudulent activities.

Healthcare Fraud Detection Based on Trustworthiness of Doctors

TLDR
The numerical validation with a healthcare dataset demonstrates that healthcare fraud by misdiagnosis in healthcare treatments can be successfully detected by employing the developed fraud detection approach and introduces the copy precision behavior in the treatment sequences of patients, which is a critical metric to learn the trustworthiness of doctors.

Fraudster Detection Based on Modularity Optimization Algorithm

TLDR
Fraudster Detection Based on Modularity Optimization Algorithm (FDMOA) approach is developed to find doctor fraudsters in a good accuracy, which models the medical insurance records as a heterogeneous weighted network of doctors and medicines, and uses a modularity optimization algorithm to divide doctors and drugs into corresponding communities on a heterogeneity network.

Medical Knowledge Graph to Enhance Fraud, Waste, and Abuse Detection on Claim Data: Model Development and Performance Evaluation (Preprint)

TLDR
The medical knowledge graph–based method successfully identified suspected cases of FWA (such as fraud diagnosis, excess prescription, and irrational prescription) from the claim documents, which helped to improve the efficiency of claim processing.

Medical Knowledge Graph to Enhance Fraud, Waste, and Abuse Detection on Claim Data: Model Development and Performance Evaluation

TLDR
The medical knowledge graph–based method successfully identified suspected cases of FWA (such as fraud diagnosis, excess prescription, and irrational prescription) from the claim documents, which helped to improve the efficiency of claim processing.

Automatic Detection of Excess Healthcare Spending and Cost Variation in ACOs

TLDR
The utility of the proposed framework on datasets from a large ACO in the United States to successfully identify unwarranted variation in therapeutic procedures even in low cost claims that had previously gone unnoticed are demonstrated.

Outlier Detection in Inpatient Claims Using DBSCAN and K-Means

TLDR
This study aims to determine the pattern of data on the occurrence of fraud based on the formation of data groupings by combining claims for inpatient bills and patient bills from hospitals in 2020 and using DBSCAN and KMeans to form clusters.

A Framework for Fraud Detection in Government Supported National Healthcare Programs

  • Irum MatloobS. Khan
  • Medicine
    2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)
  • 2019
TLDR
A framework for detecting fraudulent insurance claims is proposed by creating time series, traces of every transaction to identify invalid procedures and claims to increase the quality and efficiency of healthcare.
...

References

SHOWING 1-10 OF 19 REFERENCES

Outlier Analysis

TLDR
Outlier Analysis is a comprehensive exposition, as understood by data mining experts, statisticians and computer scientists, and emphasis was placed on simplifying the content, so that students and practitioners can also benefit.

Community detection in graphs

Isolation Forest

TLDR
The use of isolation enables the proposed method, iForest, to exploit sub-sampling to an extent that is not feasible in existing methods, creating an algorithm which has a linear time complexity with a low constant and a low memory requirement.

Modularity and community structure in networks.

  • M. Newman
  • Computer Science
    Proceedings of the National Academy of Sciences of the United States of America
  • 2006
TLDR
It is shown that the modularity of a network can be expressed in terms of the eigenvectors of a characteristic matrix for the network, which is called modularity matrix, and that this expression leads to a spectral algorithm for community detection that returns results of demonstrably higher quality than competing methods in shorter running times.

Group-in-a-Box Layout for Multi-faceted Analysis of Communities

TLDR
Group-In-a-Box (GIB) is proposed, a meta-layout for clustered graphs that enables multi-faceted analysis of networks and uses the tree map space filling technique to display each graph cluster or category group within its own box, sized according to the number of vertices therein.

A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise

TLDR
DBSCAN, a new clustering algorithm relying on a density-based notion of clusters which is designed to discover clusters of arbitrary shape, is presented which requires only one input parameter and supports the user in determining an appropriate value for it.

Big data: The next frontier for innovation, competition, and productivity

The amount of data in our world has been exploding, and analyzing large data sets—so-called big data— will become a key basis of competition, underpinning new waves of productivity growth,

The Health Insurance Portability and Accountability Act.

  • A. Meyer
  • Political Science, Medicine
    Tennessee medicine : journal of the Tennessee Medical Association
  • 1997
TLDR
The Health Insurance Portability and Accountability Act, also known as HIPAA, was designed to protect health insurance coverage for workers and their families while between jobs and establishes standards for electronic health care transactions.

Latent Dirichlet Allocation

Drug wars in the United States.

TLDR
The recent declaration by President George Bush of a war on drugs raised few eyebrows here in the United States, but the most visible effect of the announcement has been to make many people confront the failure of traditional prohibition style policies in controlling illicit drug use among American ghetto dwellers and middle class youth alike.