Fraud and Abuse in Healthcare - Provider and Funding Organisations

Healthcare fraud, waste, and abuse (FWA) are huge problems that affect consumer ecosystem. Hundreds of billions of dollars are lost to healthcare FWA and revenue leakage on an annual basis. These losses lead to increased healthcare costs and subsequently increased insurance premiums.

Given the scope and scale of national healthcare, advanced data science is necessary to detect and mitigate FWA.

Many types of fraud are perpetrated on the healthcare system. Here is a sampling of common patterns found in healthcare fraud:

Provider Fraud

• Billing for services that are not actually performed
• Performing medically unnecessary services solely for the purpose of generating insurance payments
• Unbundling — billing each stage of a procedure as if it were a separate treatment
• Use of a single patient ID to generate billing across multiple providers
• Upcoding — billing for more costly services than the ones actually performed
• Home healthcare companies demanding payment for treating clients actually in the hospital
• Home healthcare companies and visiting nurses billing additional amounts
• Patient transportation services claiming charges for patients who were never moved
• Durable Medical Equipment (DME) claims for services and supplies not provided
• Using stolen patient IDs to submit claims
• Billing cosmetic surgeries as necessary repairs
• Routinely overusing modifiers that exempt claims from editing
• Claiming expenses through free prescriptions 
• Excessively charging more than the unit thresholds
• Billing for individual services within a global surgery billing period

Insurance Subscriber Fraud

• Falsifying records of employment/eligibility to obtain a lower premium
• Filing claims for medical services that were not actually received
• Using another person’s coverage or insurance card to illegally claim the insurance benefits
• Falsifying information on health insurance exchange to obtain government subsidies,

Data science technologies can help in healthcare FWA detection and prevention in a number of important ways:

• Detecting the patterns of FWA in the billing produced by doctors and hospitals using a proprietary bottom-up Ensemble method

• Profiling and segmenting claimants to identify those who are likely to commit fraud using unsupervised learning methods
• Identifying connections among fraudsters via social network analysis
• Detecting abnormal medical event sequences for the patients
• Defining the similarity between claims to identify hidden claims duplicates  
• Detecting fraud by applying analytics to huge volumes of Medicare claims data and using a combination of anomaly detection, business rules, and predictive models.
• Revealing fraudulent activities by analyzing unstructured data (e.g. Tweets, e-mails, etc.) using advanced text analytics
• Incorporating user inputs and domain knowledge by implementing feedback loops in the analytics models

Machine Learning for Fraud Detection

• An efficient FWA analytics solution requires a combination of advanced predictive modeling algorithms, a user-friendly interactive interface, efficient workflow management, and the ability to seamlessly integrate with the existing system. Many existing FWA solutions face the challenge of addressing them effectively. For example:

1. Rules-based approaches utilize simple logistics from known schemes, obvious patterns, hotlists, and retrospective review. They can be both too aggressive, flagging too many suspects for review, which wastes resources with false positives, and too conservative, failing to detect ever-changing FWA and resulting in many false negatives. Rules are also time-consuming to maintain and always require subject-matter expertise to update with additions or edits.
2. Many predictive modeling solutions are limited by the statistical approaches and data that are utilized to build the models. First of all, these models are static and can only capture FWA patterns similar to historically identified fraud cases that exist in the model building data. Secondly, these models look at FWA patterns from a subset of the claims, beneficiary, and provider levels and in isolation. As a result, the anomaly detection model will misjudge aberrant behavior without fully considering the context, which results in a large number of both false positives and false negatives.