DME Revenue Cycle Management Case Study: 13X ROI & $11.6M AR Recovery
A Texas-based DME organization reduced denials from 23% to 9%, recovered $11.6M in aged accounts receivable, and achieved 13X ROI in four months using Anka's AI-powered revenue recovery platform, without adding billing headcount. Monthly collections rose 32%, 90+ day AR fell from 79% to 43%, and cost to collect dropped 60%.
Where the Leakage Was Hiding
Durable Medical Equipment (DME) providers face a revenue cycle unlike most other specialties. Recurring billing, Medicare documentation requirements, complex modifier rules, rental payment schedules, and payer-specific reimbursement policies create significant leakage across the post-submission claim lifecycle.
This Texas-based DME organization was experiencing rising denial rates, aging accounts receivable, and widespread underpayment issues. Within four months of implementing Anka's AI-powered revenue recovery platform, the organization reduced denials from 23% to 9%, recovered $11.6 million in aged AR, increased monthly collections by 32%, and achieved a 13X return on investment.
Reduced claim denial rates from 23% to 9% in four months · Increased monthly collections from $1.1M to $1.45M · Recovered $11.6 million in aged accounts receivable · Reduced 90+ day AR from 79% to 43% · Lowered cost to collect by 60% · Achieved 13X ROI on the aged AR recovery initiative · Improved DME revenue cycle performance without increasing billing headcount.
Top Revenue Cycle Challenges for DME Providers
Unlike many healthcare specialties, DME billing involves recurring monthly claims, Medicare and Medicaid documentation requirements, prior authorizations and medical necessity reviews, modifier-dependent reimbursement structures, rental billing schedules, and multi-month claims management processes. These complexities increase the likelihood of denials, delayed collections, and reimbursement discrepancies. For this provider, revenue leakage was occurring across three areas: claim denials, underpayments, and aging accounts receivable. Together, these issues were constraining cash flow and driving up the cost of collections.
- High Claim Denial Rates (23%): Claims involving CPAP devices, mobility equipment, and infusion therapies were frequently denied due to medical necessity documentation requirements, missing CMNs, and payer-specific policy variations.
- Undetected Underpayments: Modifier-based reimbursements involving KX, NU, and RR modifiers were routinely paid below contracted rates. With no automated reconciliation process in place, many underpayments went unnoticed and unrecovered.
- Excessive AR Aging: Nearly 79% of the organization's AR sat in the 90+ day bucket. High-value claims were aging out, timely filing windows were closing, and staff capacity stayed focused on current-period claims.
- Rising Cost to Collect: Manual processes and outsourced billing resources were creating inefficiencies while collections remained flat, leaving the organization needing a scalable approach to revenue recovery.
Industry Benchmarks vs. Client Results
Industry benchmark comparisons alongside client performance metrics highlight the scale of the operational improvement achieved after deployment.
Revenue Cycle Metric · Benchmark vs. Before/After Anka
| Revenue Cycle Metric | Industry Benchmark | Before Anka | After Anka |
|---|---|---|---|
| Denial Rate | 18.7% | 23% | 9% |
| 90+ Day AR | 24% | 79% | 43% |
| Monthly Collections | N/A | $1.1M | $1.45M |
| Open AR Balance | N/A | $39M | $27.4M |
| Underpayment Recovery | Mostly Manual | Limited Visibility | Automated |
| Cost to Collect | Industry Pressure Increasing | Baseline | 60% Lower |
How Anka Executed the Turnaround
ANKA's execution layer targeted all three leakage sources simultaneously: denials, underpayments, and aged AR, running autonomously so the billing team's time went to exceptions that genuinely needed human judgment.
Autonomous Denial Management
Denials were recurring, systemic, and often left unresolved due to staffing limitations. Anka's AI-driven engine analyzed denial codes and reimbursement patterns, identified documentation deficiencies, generated payer-specific appeals, submitted them electronically, and tracked outcomes, escalating only complex exceptions for human review. The denial rate fell from 23% to 9% within four months, significantly improving clean revenue recovery and reducing preventable write-offs.
Underpayment Recovery
Many claims were being reimbursed below contractual rates without detection, hidden inside rental billing schedules, bundled equipment reimbursements, and modifier-specific payments. Anka compared every remittance against contracted fee schedules, audited bundled item reimbursements, monitored rental payment schedules, and initiated recovery actions automatically, turning underpayment recovery from a largely invisible issue into a proactive, continuous process.
Aged AR Reduction
With 79% of AR extending beyond 90 days, valuable claims were being neglected while staff focused on newly submitted work. Anka's autonomous AR engine prioritized claims by recovery probability and payer behavior, maintained consistent follow-up schedules, and automated payer-specific outreach and escalation, reducing 90+ day AR from 79% to 43% while recovering $11.6 million in aged balances.
Why AI Revenue Cycle Automation Matters
Traditional revenue cycle management systems are designed to provide reporting, dashboards, and recommendations. Recommendations alone do not recover revenue. Execution does. AI-powered revenue cycle automation enables DME providers to:
- Automate denial analysis and appeals
- Detect payer underpayments in real time
- Prioritize and manage AR follow-up automatically
- Increase collections without expanding staffing
- Improve cash flow and financial predictability
- Reduce administrative burden on billing teams
For DME organizations facing increasing reimbursement pressure and staffing shortages, autonomous revenue recovery offers a scalable path to improving financial performance.
Results After Four Months
All results were achieved within four months of deployment and represent realized financial outcomes rather than projected estimates.
Performance Comparison: Before & After Anka
| Metric | Before Anka | After Anka | Impact |
|---|---|---|---|
| Monthly Collections | $1.1M | $1.45M | +32% |
| Denial Rate | 23% | 9% | -60% |
| 90+ Day AR | 79% | 43% | Improved Cash Flow |
| Open AR Balance | $39M | $27.4M | $11.6M Recovered |
| Cost to Collect | Baseline | -60% | Operational Efficiency |
| ROI | N/A | 13X | Revenue Recovery Success |
"We weren't short on effort; we were short on revenue cycle intelligence. Anka fundamentally changed how we saw, prioritized, and acted on revenue. Within weeks, we were collecting on claims we had written off months ago."VP, Revenue Cycle Operations, Texas DME Group
