Published by Becker’s Healthcare, October 28, 2026 | Author: Aspirion
Contract Modeling: You Can’t Recover What You Can’t Price
A claim comes back paid, the account closes, and the team moves on. That works only if the payment was right. Without knowing what a claim should have paid under its contract, an underpayment looks like every other paid claim. AI now makes it practical to know that number for every claim.
Fewer Denials, Same Cash Problem
A Kodiak Solutions analysis found the initial denial rate fell to 10.63% in the first half of 2026, down from 12% a year earlier. But payer takebacks rose to 1.57% of accounts receivable, up from 1.38%, a 13.8% increase. Post-payment recoveries fell 12.2%. Pressure has moved later in the cycle, to places where it is harder to see.
Where Underpayments Hide
Payer agreements layer rate exhibits, amendments, and interdependent terms. Analysts typically hand-code each term into a database, which is slow, error-prone, and needs rework whenever the contract changes. Lesser-of terms, stop-loss thresholds, carve-outs, and pass-throughs add more room for error. In the article’s example, a $27,000 DRG payment plus a $7,500 implant pass-through should total $34,500. If the pass-through was never modeled, a $27,000 payment looks correct, and nobody collects the $7,500.
Pricing Every Claim
A large language model reads the agreement and extracts its rates and rules, and a rules engine turns them into pricing logic. Claims are priced in seconds instead of days, and every claim is checked rather than a sample. Each claim is scored on how likely it is to be a true underpayment, and each expected payment is explained rule by rule with the contract language that supports an appeal. Experienced reviewers check every extracted rule against the contract first, because a model can misread a rate table or record the same rule twice.
Seeing the Pattern
Sorting underpayments by payer, service line, and facility turns one-off errors into recognizable patterns. In an HFMA and Trek Health survey, 68% of provider leaders cited payer policy changes not reflected in contracts as a leakage risk, but only 26% proactively track them. Regulators are also paying attention. CMS intends to use Worksheet S-12 data on Medicare Advantage negotiated rates to set MS-DRG weights beginning in fiscal year 2029.
Lower denial rates don’t show whether you’re collecting what your contracts promise.
Read the full article here.