Learn more →
Back to WorkCase Study · AI Transformation

AI Appeal Generator:
Recovering a $2.5M Business Case

Turning around an underperforming generative AI deployment at a leading revenue cycle management company by re-architecting document ingestion, narrowing the target population, and replacing usage metrics with rework and outcome metrics.

ClientConfidential
Business Case~$2.5M EBITDA
Run-Cost Reduction~60%
Records Processed130-700 pages
AI Portfolio60+ Initiatives

Devinci Partners was engaged to oversee a portfolio of 60+ AI initiatives across product, engineering, finance, and operations. This case study covers one of them.

The Challenge

A $2.5M tool realizing a fifth of its value

When a hospital's insurance claim is denied, the RCM company writes an appeal to the insurer arguing why the claim should be paid. Appeals are labor-intensive: an analyst or clinician reads the patient's electronic medical record, often 130 to 700 pages, then constructs a written argument.

The product and engineering teams built a generative AI appeal generator: ingest the EMR, draft the appeal. The business case was roughly $2.5M in annual EBITDA from analyst time savings, and it was rolled out to the entire appeals team. Two quarters after launch, telemetry showed strong usage. Realized value was roughly $0.5M.

Run cost was consuming the savings

Every appeal required converting hundreds of pages of tables, forms, and clinical notes into model-readable text. That extraction step alone was roughly 80% of the per-appeal cost, and at production volume it offset about two thirds of the projected savings.

Usage was not adoption

Analysts opened the tool, then rewrote a large share of the drafts. Telemetry recorded a use; it could not see the rework. The time savings the business case depended on were not materializing.

Underneath both was a definitional problem: “appeals” had been treated as one task. Operations knew it was several.

Our Approach

From a generic pipeline to a persona-specific one

01

Cost diagnosis

Walked the architecture step by step and attributed cost per appeal to each stage. Isolated EMR extraction (OCR and layout parsing of tables and forms) as roughly 80% of run cost. The root cause was not the model; it was sending the entire record when only a fraction was relevant to any given appeal.

02

Operational task mapping

Sat with analysts across appeal types to document what each actually reads in the EMR. A medical necessity appeal requires the patient's clinical journey over time; a DRG downgrade appeal turns on one or two physician notes. Produced a relevance map: which EMR sections matter for which appeal type.

03

Re-architecture of ingestion

Translated the relevance map into a hierarchical chunking approach with engineering: read section headers first, retrieve only relevant sections, skip tables and images where not needed, then order clinical events chronologically before drafting. Benchmarked alternative extraction vendors for the remaining OCR workload against the incumbent on cost and accuracy.

04

Adoption measurement and refocus

Surveyed the operations team to identify which appeal types the tool handled well and which were being rewritten. Redirected engineering effort to the appeal types with low rework, and defined a persona-specific roadmap for the rest. Established rework rate, not usage, as the adoption metric.

Cost Analysis

Per-appeal run cost by pipeline stage

Illustrative shares shown; actual figures are confidential. Input and output tokens were the smallest cost line. Data extraction was the largest. The original case modeled the former and omitted the latter.

EMR extraction (OCR, table and form parsing)~80%

Hierarchical chunking; only relevant sections extracted; vendor benchmark

Context assembly and chronology~8%

Second-pass agent orders retrieved sections

Draft generation (LLM inference)~7%

Unchanged

QA and formatting~5%

Unchanged

Adoption Analysis

Rework by appeal type

Telemetry showed near-uniform usage. The operations survey showed the value was concentrated in a subset of appeal types.

Medical necessity

Strong

Full clinical journey, chronological

Scale; primary focus

DRG downgrade

Weak

One or two physician notes; coding argument

Refactor per persona before re-release

Administrative / timely filing

Under review

Small set of dates and correspondence

Sequenced behind medical necessity

Legal / contractual

Under review

Contract terms, payer policy

Sequenced behind medical necessity

Business Case Reconstruction

Rebuilding the ROI on four inputs

The original case used two inputs: population and time saved. The rebuilt case used four.

Population impacted

Original caseEntire appeals team
Rebuilt caseAnalysts on appeal types with proven draft quality, expanding by wave

Productivity gain

Original caseUniform minutes saved per appeal
Rebuilt caseMeasured per appeal type, net of rework

Cost to run

Original caseNot modeled
Rebuilt casePer-appeal cost including extraction, at production volume

Capacity plan

Original caseNot defined
Rebuilt caseDefined upfront: what the organization does with the freed hours
Key Findings

What transfers to any AI deployment

01

Extraction, not inference, is the cost driver

For any workflow built on long documents, the cost of making the document machine-readable dominates model cost. Business cases that model tokens and omit extraction will overstate ROI by a wide margin.

02

“One task” is usually several

The same job title concealed at least four distinct appeal types with different evidence requirements. A generic pipeline was expensive for all of them and good for only some.

03

Usage metrics hide rework

Telemetry cannot see an analyst rewriting a draft. Adoption must be measured as output accepted without rework, which requires going to the operators directly.

04

Narrow beats broad

A tool that removes 30-40% of the work for a defined population produces bankable savings. A tool that saves 5% of everyone's time produces a spreadsheet figure that never reaches the P&L.

05

Cost to run and capacity plan belong in every case

The two inputs most often omitted are the two that decide whether value is realized: what it costs to operate at volume, and what the organization will do with freed hours.

Outcome

Run cost down ~60%; value re-baselined by appeal type

Re-architected ingestion reduced per-appeal run cost by roughly 60% while maintaining draft quality on analyst review. The tool was refocused on the appeal types where analysts accept the output, with a persona-specific roadmap for the remainder.

The next phase closes the loop: capturing appeal outcomes (overturned, upheld, partially paid) and feeding them back into draft quality, and ultimately into a model that predicts which denials are worth appealing at all.

The engagement also produced the operating framework now applied across the client's AI portfolio: four-input business cases, narrow pilots of 30-60 users of a single persona, and rework rate as the adoption metric.

Discuss a Similar Engagement