Independent Research Project · 2018–Present

The error that passes every review.
This research finds it.

ContextRx is an independent research project exploring how NLP and machine learning can detect contextual word errors in pharmaceutical documents and drug labels — correctly-spelled words used in the wrong clinical context. Eight years in development across five architectural iterations, now operating as a production system scanning FDA-approved drug labels and surfacing errors that pass through existing pharmaceutical quality systems, including regulatory review.

Corpus: 34,201 FDA-approved drug label documents · Research use only

Prescribing Information — Section 2.1SCAN ACTIVE

Advise to report any signs of infection immediately.

Titrate based on renal function and patient response.

Microsoft WordCorrect ✓
GrammarlyCorrect ✓
Standard Verification ToolsCorrect ✓
ContextRx▶ 2 Errors Found
8 years

In development, as an independent research effort

5

Architectural iterations, from rule-based to learned context models

34,201

FDA-approved drug label documents in the research corpus

10/10

vs. Grammarly's 7/10 on a curated pharma context-error benchmark*

* Internal benchmark across curated pharmaceutical context errors; methodology available on request. Results are research findings, not a validated regulatory control.

⚠ The Problem

The errors that slip through every review

These aren't typos. They're correctly-spelled words in the wrong clinical context — invisible to spellcheckers, undetectable by text-comparison tools, and consequential when they reach a published label. The examples below are representative of the error class this research targets.

Advise patents to report any signs of infection immediately.

Word: PASSGrammarly: PASSContextRx: FLAGGED

patentspatients

Patient instruction error — FDA deficiency letter risk

Titrate does based on patient renal function and weight.

Word: PASSGrammarly: PASSContextRx: FLAGGED

doesdose

Dosing instruction corrupted — prescribing error risk

Contraindicated in patients with hepatic inflammation (Child-Pugh B or C).

Word: PASSGrammarly: PASSContextRx: FLAGGED

inflammationimpairment

Wrong contraindication category — patient safety impact

Store at controlled room temperate (20°–25°C / 68°–77°F).

Word: PASSGrammarly: PASSContextRx: FLAGGED

temperatetemperature

FDA-defined storage condition absent — recall risk

Contraindicated in patients with placenta group in clinical trials.

Word: PASSGrammarly: PASSContextRx: FLAGGED

placentaplacebo

Clinical trial exclusion criterion corrupted

Administer 10 mg orally one daily with or without food.

Word: PASSGrammarly: PASSContextRx: FLAGGED

oneonce

Dosing frequency ambiguous — patient harm risk

◎ Method

Modeling pharmaceutical context, not spelling

The research question: can a model learn what a word should mean in a regulated clinical passage well enough to flag a real word that is wrong there? Five architectural iterations over eight years — from rule and n-gram baselines to learned contextual representations fitted on label text — converged on the pipeline below.

01

Ingest the document

Any pharmaceutical document — Package Insert, SmPC, Patient Leaflet, submission text. Processing runs locally; no document content leaves the machine it runs on.

02

Model the context

The NLP pipeline, built over five architectural iterations and fitted on a corpus of 34,201 FDA-approved labels, scores every token for semantic fit in its pharmaceutical context — clinical meaning, not spelling.

03

Surface candidate errors

Each flag is reported with the substitution candidate, the clinical risk category, and the surrounding context, so a human reviewer can adjudicate the finding.

◎ Findings

Errors found in live, FDA-approved labels

The system currently runs in production against published drug labels. It identifies contextual errors that have already passed through pharmaceutical quality systems, including regulatory review — which is the central empirical finding of this project. Examples below are anonymized; findings are reported for research purposes, not as regulatory determinations.

Anonymized OTC analgesic

Adults: take one tablet by mouth once every six ours, not to exceed 4 doses in 24 hours.

hours

Live in market. Surfaced by a research scan of the DailyMed corpus.

Anonymized Rx anticoagulant

Avoid in patients with severe hepatic inflammation (Child-Pugh C).

impairment

Live in market. Surfaced by a research scan of the DailyMed corpus.

Anonymized pediatric antibiotic

Store reconstituted suspension at controlled room temperate.

temperature

Live in market. Surfaced by a research scan of the DailyMed corpus.

🔬 Try It

Run the system on sample text

Paste a passage of label or regulatory text to see the context scan behave. Please use non-confidential text — this page is a hosted sandbox, not the offline research build.

document.txt

Hosted sandbox. The research build runs fully offline with zero data egress.

⌛ Awaiting input — scan results appear here
◎ Contact

Get in touch about the research.

If you work on labeling, regulatory writing, pharmacovigilance, or NLP and want to discuss the method, review the findings, or explore collaboration, send a note. Please don't include confidential or unpublished document content.

What to expect

  • 1This is a research inquiry, not a sales conversation — nothing is being sold
  • 2Reply typically within a few days; the project runs outside working hours
  • 3Happy to share methodology, benchmark design, and error taxonomy
  • 4Open to collaboration, peer review, replication, and dataset discussion

No mailing list. No sales follow-up. Nothing is being sold.

∞ Scope & Independence

An independent project, run on its own time

ContextRx is a personal research project conducted independently of any employer, client, or sponsor. It is not a commercial product, it is not for sale, and its findings carry no regulatory weight. The architecture is offline-first by design so that experiments can run on sensitive text without any data leaving the machine. Findings are shared to invite scrutiny of the error class, not to make claims about any specific product or manufacturer.

↔ Prior Art

Where existing tools stop, and this research begins

This project does not aim to replace any existing tool. It isolates a single error class that general-purpose spelling, grammar, and proofreading systems are not designed to detect, and asks whether it can be modeled.

CapabilityMicrosoft WordGrammarlyContextRx (research)
Misspelled words✓ Included
Grammar & styleNot the focus
Version-to-version text comparisonOut of scope
Artwork & barcode verificationOut of scope
Pharma context errors (patents→patients)✗ Missed✗ Missed✓ Research focus
Fitted on FDA label text✓ 34,201 docs
Runs fully offline✗ Cloud-only✓ Offline-first
Logged, reviewable findings✓ Full audit log
Benchmark context-error score*n/a7/1010/10

An open question, eight years in.

Contextual word errors reach published, FDA-approved labels today. This project exists to measure how often, and to test whether language models can catch them. Scrutiny, replication, and collaboration are all welcome.

8 yrs

Independent development, five architectural iterations

34,201

FDA-approved label documents in the research corpus

100%

Offline research build — no document content leaves the machine

Open the research system — demo.contextrx.io →