NewMissing Records Detection: flags every visit, provider, and date missing from the file. See how →
HomeSolutionsWorkers' CompensationBlack Lung Claim Review
BLACK LUNG CLAIM RECORD REVIEW

2 x-rays, 2 pulmonary studies, 2 blood gas studies — pick the right ones.

Black lung claim record review reads the full federal claim file against the standard that grades it. §725.414 caps each party at 2 x-ray readings, 2 pulmonary function studies, and 2 blood gas studies, so we check every value against Part 718's height-and-age thresholds before you choose which 2 to file.

Click any row → the source page it cites
Evidence inventory · Case #IME-4812 indexed
Adams, Timothy · black lung claim file
342 pp / 2 packets received logged
11 duplicate pages removed free
p.140 — wrong patient quarantined
Pages 342 Documents 27 Cited 100%

The thresholds are printed. So is the exhibit cap.

We do not build for a case type until we can name the standard that defines a correct output and the person who grades the file against it. Federal black lung claims put both in the regulation, down to the numeric value.

That is what makes the case type buildable. A qualifying pulmonary function value is a table lookup on height and age, not an opinion, and the evidence cap is a counting rule.

The rulebook and the referee
The rulebook
  • 20 CFR Part 718, Appendices A through C — exact pulmonary function and arterial blood gas thresholds, tabulated by the miner's height and age
  • 30 USC §921(c)(4) — the 15-year rebuttable presumption, argued from coal mine employment history and totally disabling respiratory impairment
  • 20 CFR §725.414 — strict evidentiary limits: 2 x-ray readings, 2 pulmonary function studies, 2 blood gas studies, and 2 medical reports per party
  • Exceed the §725.414 limit and the evidence is excluded. There is no later cure for an exhibit designated in the wrong slot.
The referee
  • The District Director, who issues the proposed decision and order on the developed record
  • Then the DOL Office of Administrative Law Judges, the Benefits Review Board, and the federal Court of Appeals
  • Under §725.414 a mis-selected exhibit is fatal, because the party has already spent one of its 2 slots
  • The approval rate is 32%, so roughly 2-thirds of the work product is graded as insufficient
Roughly 12,400 files worked a year at about 15 hours each, in federally grant-funded clinics From 10¢ to as low as 5¢/page here, duplicates free
Evidence inventory · Case #IME-4812 cited 100%
Production342 pp / 2 packets · 11 deduplicatedlogged
Chest x-ray readingsReader, credentials, date, classificationindexed
Pulmonary and blood gas studiesValues with height, age, test datetabulated
Coal mine employment historyHandwritten forms and decades-old carbonsdegraded
4 evidence categories · cited 100% · no eligibility calls
What the file looks like

A working life, produced in pieces.

A federal black lung file runs 1,000 to 4,000 pages, with 2,500 about typical. It is rarely one production. Clinic charts, hospital admissions, operator-ordered examinations, prior claims, and decades of coal mine employment forms arrive separately, in different formats, with the same films and reports reappearing across packets.

Much of it is hard to read before it is hard to analyse: handwritten employment forms, carbon copies, and scans of scans, next to typed reports whose numeric values are the entire point.

6,120
claims filed in FY2024, up from 5,566
4,242
claims pending at the same point
$175M
paid in Part B and Part C benefits
32%
approval rate on the graded record

Claim, pending, and benefit figures: DOL, primary source.

What we'd build with you

4 steps, starting with one real file.

01

Send one real file

A claim file you already hold, in whatever shape it arrived. We do not retrieve records from providers or the Department of Labor; you bring what you have, degraded scans and handwritten employment forms included.

02

We return the read

A full inventory of the §725.414 categories: every x-ray reading, pulmonary function study, blood gas study, and medical report, with dates, authors, values, and the page each came from. In the demo case, a wrong-patient page is quarantined before the read starts.

03

We scope the build

Together we decide what the output should be: the evidence inventory, the Part 718 table row placed beside each value, the conflicting-readings view, or the chronology behind the employment history. Then we scope it against your intake volume.

04

You run it

Your benefits counselor, lay representative, or clinic coordinator works from the inventory and designates the exhibits. The platform never designates evidence, never invokes a presumption, and never decides a claim.

Audit trail · Case #IME-4812 exportable
08:12Packet received · 342 pp / 2 packetssystem
08:3111 pages deduplicatedsystem
08:44p.140 flagged — wrong patientsystem
08:54Evidence inventory complete · cited 100%system
09:20Inventory reviewed · citations verifiedreviewer
09:26Inventory exported · exhibits designated off-platformreviewer
Every access logged · file deleted 30 days after delivery
Why Medrecords AI

The rules the platform never breaks.

Medrecords AI EVERY LINE CITED
CASE #IME-4812 · ADAMS, T.342 pp
2/14 — ER visit, right knee p.4
4/18 — arthroscopic surgery p.61
p.140 — wrong patient quarantined
Medrecords AI
Read every page · cite every line

HIPAA, under a signed BAA

Every file is handled under our Business Associate Agreement, from the first byte.

Never trains a model

Your records are never used to train any AI model — ours or anyone else's.

Every line cited

If we can't cite it, we don't say it. Every sentence links to its source page.

Deleted after delivery

Files are deleted 30 days after delivery, with a full audit log of every access.

Powered by the platform

7 capabilities behind every evidence inventory.

The black lung record review is one deliverable of the same platform that reads, sorts, and cites the whole record.

Medical Records OCR

Handwritten employment forms, carbon copies, and scans of scans read in full — nothing skipped, nothing guessed.

IN ACTION · 342 pp / 2 packets → 27 documents, read in full

Medical Table Extraction

Spirometry and blood gas tables come out as values, not prose: FEV1, FVC, MVV, pO2, pCO2, with the height and age printed on the same study.

IN ACTION · study table → value, height, age, test date

Medical Chronology

Decades of employment and treatment records land on one timeline, synced to every source page, so prior claims sit next to current studies.

IN ACTION · multiple productions → one continuous timeline

Condition Progression Tracking

The same clinical measure across years of studies, lined up so a trend is visible instead of buried in separate reports.

IN ACTION · repeat studies → one trend, every point cited

Medical Record Deduplication

Decades of mine employment and treatment records arrive across multiple productions, and the same x-ray reading or PFT study can land in the file twice. Every duplicate is confidence-scored and collapsed to one canonical page — before it burns one of the 2 exhibit slots §725.414 allows.

IN ACTION · 342 pp / 2 packets → 27 documents, duplicates collapsed

Missing Records Identification

A prior claim or treatment note is referenced in the file but the underlying record was never produced. The gap is named before an exhibit slot is designated for it, since §725.414 leaves no room to designate twice.

IN ACTION · study referenced, not in the file → the gap named before filing

Cross-Exam Simulator (beta)

Before the Office of Administrative Law Judges hearing, this beta tool drafts the likely cross-examination lines from the file's own inconsistencies — a PFT that doesn't match the B-read, a history that shifts between visits. A rehearsal tool, not a legal opinion.

IN ACTION · beta · file inconsistencies → cross-exam lines rehearsed before the hearing
Adjacent federal programs we also read: EEOICPA claim review and RECA claim review.
FAQ

Black lung claim evidence, answered.

4 categories, each capped by 20 CFR 725.414: chest x-ray readings, pulmonary function studies, arterial blood gas studies, and physicians' medical reports, alongside the employment history that establishes coal mine work. We read the whole production, index every one of those items with its date, its author, and its page cite, and put the full set in front of you. Which items make the strongest record is counsel's judgment, not ours.

Part 718 Appendices A through C set exact qualifying values by the miner's height and age, so an FEV1 or a pO2 only means something next to the height and age recorded on that study. We extract the values, the height, the age, and the test date, cite each to its page, and place the applicable table row beside them. Whether a study qualifies is the adjudicator's call.

No. An ILO classification is made by a physician holding a NIOSH B reader certification, and nothing on the platform replaces that. What we do is index the readings already in the file: the reader, the credentials claimed, the date, the classification given, and the page it sits on. When 2 readers disagree on the same film, we surface both readings side by side instead of picking one.

No. The rebuttable presumption under 30 USC 921(c)(4) is a legal determination made by the District Director, and then by an administrative law judge if the claim is contested. We assemble the record it is argued from: the coal mine employment history, the conditions of that employment, and every piece of respiratory impairment evidence in the file, each cited to its source page. We never conclude that a presumption is established or rebutted.

Section 725.414 lets each party submit only 2 x-ray readings, 2 pulmonary function studies, 2 blood gas studies, and 2 medical reports. Exceeding the limit gets evidence excluded, and a mis-selected exhibit cannot be cured later. We give you a complete inventory of everything in those 4 categories, with dates, authors, values, and page cites, so the designation is made with the whole file visible. The designation itself stays counsel's decision.

Send one file. We'll tell you what we can read.

No obligation. If the case type is buildable we'll scope it; if it isn't, we'll say so.