Is Your Payment Integrity Strategy Really Working?

Keeping members healthy is important, yet no one should have to pay more than necessary. Unfortunately, many healthcare services are billed incorrectly, costing payers and providers time and money.

Lumiata’s payment integrity solution automates the claims review process by using artificial intelligence and machine learning to provide better outcomes for both parties. Whether it is pre-bill or pre-pay, we can help your organization, too.

Doing Things “How They’ve Always Been Done” Is Costing You more Money

How many times have you paid a bill only to later realize you really shouldn’t have had to pay that? Even with your internal team auditing suspicious claims before paying, many incorrect claims still slip through the cracks. It’s estimated that 80% of medical bills have errors.[i]

While vendors will catch some of the incorrect claims that your internal team misses, these vendors often keep a percentage of the money found, which can quickly add up. Do you really want to share the savings that you could have found yourself?

These billing errors don’t only affect payers, however. As a provider, it’s important to make sure your claims are accurate before you submit them to the payer. If a claim is flagged as being suspicious, it can prevent you from being properly paid.

Payment integrity is in the best interests of both parties. Lumiata’s solution can drastically improve your payment integrity outcomes.

The New Approach to Payment Integrity

Lumiata uses AI and machine learning to ensure claims are billed and paid correctly. Our payment integrity approach automatically recognizes outlier patterns in the data to improve existing rules, flag risk factors, and assign risk scores to each incoming claim, or outgoing bill.

For payers, this means we help you identify claims that are suspicious from a patterns-of-care perspective and Subject Matter Expert (SME) analysis. This allows your internal team to identify incorrect bills before they’re paid. It also enables you to keep more of the savings you would have otherwise had to share with vendors.

For providers, we make sure the bills you submit are paid the first time, helping you keep your cash flow as smooth and predictable as possible and helping ensure you get paid for the services you provide.

How It Works

Using artificial intelligence and machine learning, Lumiata identifies claims that are outliers from typical patterns of care. We find these using outlier model techniques which can identify claims that break clear rules, identify claims where a service was part of a bundle but was billed twice, identify the specific attribute that causes a claim to be an outlier, and more.

Our payment integrity solution works in two phases:

Phase 1: Getting ML Ready

During Phase 1, we prepare your data for machine learning, onboard the data, and run the first versions of our models based on what we already know from our vast data asset.

  • Data preparation and transformation, including data normalization, enrichment, and cleansing (ETL)
  • Statistical data analysis
  • SME/expert data analysis
  • Model predictions v1.0

Phase 2: ML Models

During Phase 2, we begin to tweak our models based on your specific cohort of data and patterns of care to identify additional outlier claims relative to your data set.

  • Retrain Models – model predictions v2.0
  • Combine outcomes from phase 1/2
  • Provide claim risk score model with factor explainability

Our payment integrity solution looks at targeted probabilistic features (diagnosis code data, procedure data, and ER level process data) as well as targeted SME expertly defined edits (IPO, AOC, MUE, P2P, etc.) to determine the claim risk score. By layering machine learning on top of a traditional SME approach, we provide a more comprehensive approach to identifying outlier claims for your internal team to investigate.

Benefits of Lumiata’s Payment Integrity Solution

Our solution provides several benefits for your organization.

Discover more incorrect claims: We provide an estimated overpayment identification potential of 30-40%. 

Save money: For a flat fee, we’ll select the best claims for your internal teams to review and let your vendors take care of the rest. This reduces the number of claims sent to vendors as well as the amount of savings you’ll have to share with them.

Benefits for payers: Find more faulty claims before you pay them

Benefits for providers: Make sure you get paid for your services the first time by screening them for suspicious care and billing patterns

Case Study and Results

Lumiata recently applied our payment integrity solution to a client’s data and achieved outstanding results. The scope of the project included 303,652 unique claims, across $4.02B in claim spend (a limited data set). For this project, we focused on ambulatory surgery centers and behavioral health claims.

Before Lumiata, the client’s internal model identified 18.1% of claims (55,049 claims) as being outliers.

In our first step (statistical data analysis), Lumiata identified 20.9% of claims as outliers (63,321 claims). These accounted for +$82.2M in incremental suspect claim overpayment identifications.

Our next step (SME analysis) identified an additional 0.5% of claims as outliers (6,371 claims). These accounted for +$16.8M in incremental suspect claim overpayment identifications.

Our third step (ML outlier detection) identified an additional 9.0% of claims as outliers (15,308 claims). These accounted for +$149.3M in incremental suspect claim overpayment identifications.

Lumiata identified a total of 30.4% of claims as outliers – a 12.3% increase over what the client’s internal scoring models had found. This equated to an incremental savings opportunity of $248M. As this study was based on a limited data set, we believe the potential savings to be even greater for any client’s full data set, with a typical overpayment identification potential of 30-40%.

Ready to Try Lumiata?

Payment integrity is crucial to ensuring accurate billing and reducing your costs. Lumiata helps you catch more suspicious claims faster pre-bill and pre-pay, so you can save time, money, and stress. Are you ready to see how an automated payment integrity risk scoring process can benefit your organization? Visit lumiata.com/solutions to learn more.

[i] https://www.beckershospitalreview.com/finance/medical-billing-errors-growing-says-medical-billing-advocates-of-america.html