Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.


01:59 PM

Verizon Uses Predictive Modeling To Detect Health Fraud

Verizon software can spot doctors prescribing excessive amounts of medication and other trends that indicate falsified billings.

12 Innovative Mobile Healthcare Apps
(click image for larger view)
Slideshow: 12 Innovative Mobile Healthcare Apps
The telecommunication giant has just unveiled a new software platform called Verizon Fraud Management for Healthcare, a fraud detection system tailored to the healthcare industry. It uses predictive modeling technology to examine unusual patterns and trends in incoming healthcare payment requests.

The platform is designed to send potentially fraudulent claims information to case managers for investigation before payments are made. Such a system, Verizon officials say, will help mitigate the administrative and legal costs involved when health organizations pay the claim and then go after the fraudsters, which usually involves hefty legal fees and other costs associated with a recovery operation.

According to Connie Schweyen, managing principal, Verizon Connected Healthcare Solutions, the system is geared toward spotting, for example, doctors prescribing excessive amounts of medication, the unusual use of patient identification numbers to order large amounts of medical equipment, and other trends that indicate falsified billings, or show that orders were not delivered or were medically unnecessary.

"The software can detect all of those things by using the algorithms within the system," Schweyen told InformationWeek Healthcare. "The software then scores those incidents and prioritizes the various kinds of cases and medical data to ensure that they are working on the highest-cost, most-at-risk cases first."

[ Today's mobile devices have transformed medical care in unprecedented ways. For an in-depth look at exactly how clinicians are using these tools, tune into the InformationWeek Healthcare Webcast The Mobile Point of Care: Making the Right Choices]

In addition to detecting fraud, waste, and abuse in healthcare claims payment systems, the technology also offers customers the ability to:

-- Create faster responses to address potential risks.

-- Provide strategic insight into systemic issues to drive improvements or make necessary policy changes.

-- Generate executive-level management reports to measure results and determine return on investment.

The Centers for Medicare & Medicaid Services (CMS) already has begun using Verizon's fraud management platform as part of a Northrop Grumman-led team to detect fraud and waste in CMS' Medicare Program.

The technology, which CMS started using in July, is a customized version of the software platform Verizon uses for its own fraud detection programs. CMS uses the software to examine incoming Medicare program claims and routes those that might be fraudulent to case managers for investigation.

According to the latest statistics from the U.S. Department of Health and Human Services, in 2009, national health expenditures totaled $2.5 trillion representing 17.6% of the U.S. gross domestic product. Of that number, fraud accounted for as much as $260 billion, or at least 10% of annual U.S. healthcare expenses.

The Verizon platform is available immediately and the company is targeting the software to customers at federal and state health programs as well as commercial health insurers.

"The current post-paid model used for healthcare fraud programs is highly inefficient and unsustainable," Nancy Fabozzi, Frost & Sullivan's senior industry analyst covering healthcare information technology, said in a statement. "Verizon's use of advanced software technology to evaluate and process medical claims prior to payment is indicative of the future direction of healthcare fraud prevention."

Comment  | 
Print  | 
More Insights
Newest First  |  Oldest First  |  Threaded View
Lisa Henderson
Lisa Henderson,
User Rank: Apprentice
11/17/2011 | 2:24:58 AM
re: Verizon Uses Predictive Modeling To Detect Health Fraud
Predictive modeling is used in many industries, but this is a very useful case study of how fraud protection works. I wonder in what other areas in healthcare could this be applied? I don't know, but good article.

Lisa Henderson, InformationWeek Healthcare, contributing editor
Data Privacy Protections for the Most Vulnerable -- Children
Dimitri Sirota, Founder & CEO of BigID,  10/17/2019
Sodinokibi Ransomware: Where Attackers' Money Goes
Kelly Sheridan, Staff Editor, Dark Reading,  10/15/2019
7 SMB Security Tips That Will Keep Your Company Safe
Steve Zurier, Contributing Writer,  10/11/2019
Register for Dark Reading Newsletters
White Papers
Cartoon Contest
Write a Caption, Win a Starbucks Card! Click Here
Latest Comment: The old using of sock puppets for Shoulder Surfing technique. 
Current Issue
7 Threats & Disruptive Forces Changing the Face of Cybersecurity
This Dark Reading Tech Digest gives an in-depth look at the biggest emerging threats and disruptive forces that are changing the face of cybersecurity today.
Flash Poll
2019 Online Malware and Threats
2019 Online Malware and Threats
As cyberattacks become more frequent and more sophisticated, enterprise security teams are under unprecedented pressure to respond. Is your organization ready?
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
PUBLISHED: 2019-10-17
Adobe Download Manager versions have an insecure file permissions vulnerability. Successful exploitation could lead to privilege escalation.
PUBLISHED: 2019-10-17
Sequelize, all versions prior to version 4.44.3 and 5.15.1, is vulnerable to SQL Injection due to sequelize.json() helper function not escaping values properly when formatting sub paths for JSON queries for MySQL, MariaDB and SQLite.
PUBLISHED: 2019-10-17
An issue was discovered in Bitdefender BOX firmware versions before that affects the general reliability of the product. Specially crafted packets sent to the miniupnpd implementation in result in the device allocating memory without freeing it later. This behavior can cause the miniupn...
PUBLISHED: 2019-10-17
CA Performance Management 3.5.x, 3.6.x before 3.6.9, and 3.7.x before 3.7.4 have a default credential vulnerability that can allow a remote attacker to execute arbitrary commands and compromise system security.
PUBLISHED: 2019-10-17
The Deep Security Manager application (Versions 10.0, 11.0 and 12.0), when configured in a certain way, may transmit initial LDAP communication in clear text. This may result in confidentiality impact but does not impact integrity or availability.