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. It now runs as a production system scanning FDA-approved drug labels and surfacing errors that pass through existing pharmaceutical quality systems, including regulatory review.
● Corpus: curated FDA-approved drug label documents · Research use only
Advise to report any signs of infection immediately.
Titrate based on renal function and patient response.
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.
patents → patients
Patient instruction error — FDA deficiency letter risk
Titrate does based on patient renal function and weight.
does → dose
Dosing instruction corrupted — prescribing error risk
Contraindicated in patients with hepatic inflammation (Child-Pugh B or C).
inflammation → impairment
Wrong contraindication category — patient safety impact
Store at controlled room temperate (20°–25°C / 68°–77°F).
temperate → temperature
FDA-defined storage condition absent — recall risk
Contraindicated in patients with placenta group in clinical trials.
placenta → placebo
Clinical trial exclusion criterion corrupted
Administer 10 mg orally one daily with or without food.
one → once
Dosing frequency ambiguous — patient harm risk
Errors found in live, FDA-approved labels
The system currently runs against published drug labels. Public findings are human-verified and anonymized to company class so the focus remains on the failure class, not a specific product or labeler.
Latest verified case · Severity: high
FDA DailyMed Drug Facts said "rinse with doctor" instead of "rinse with water"
doctor → water
Read the case →
Get in touch about the research.
Open for discussions regarding methodology, research findings, and secure, confidential inquiries from corporate development teams concerning technology licensing, code inspection, or IP transfer.
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
In development, as an independent research effort
Architectural iterations, from rule-based to learned context models
A curated corpus of FDA-approved drug labels
A small curated benchmark informs ongoing method development*
* Internal benchmark across curated pharmaceutical context errors. Methodology available on request. Results are research findings, not a validated regulatory control.
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? Multiple architectural iterations — from rule and n-gram baselines to learned contextual representations fitted on label text — converged on the pipeline below.
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.
Model the context
The NLP pipeline, built over multiple architectural iterations and fitted on a curated corpus of FDA-approved labels, scores every token for semantic fit in its pharmaceutical context — clinical meaning, not spelling.
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.
An independent project, run on its own time
ContextRx is an independent research project independent of any commercial sponsor, offering modular, offline-first NLP assets including custom context models, token-scoring algorithms, and a curated corpus of normalized FDA-approved labels engineered for system integration or technology transfer.
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.
| Capability | Microsoft Word | Grammarly | ContextRx (research) |
|---|---|---|---|
| Misspelled words | ✓ | ✓ | ✓ Included |
| Grammar & style | ✓ | ✓ | Not the focus |
| Version-to-version text comparison | ✗ | ✗ | Out of scope |
| Artwork & barcode verification | ✗ | ✗ | Out of scope |
| Pharma context errors (patents→patients) | ✗ Missed | ✗ Missed | ✓ Research focus |
| Fitted on FDA label text | ✗ | ✗ | ✓ Curated FDA label corpus |
| Runs fully offline | ✓ | ✗ Cloud-only | ✓ Offline-first |
| Logged, reviewable findings | ✗ | ✗ | ✓ Full audit log |
| Curated context-error study* | Not evaluated | Reference only | Method under study |
* This is an internal exploratory study, not an independent product comparison. Methodology is available on request.
Subscribe to new findings
Twice-weekly · anonymized cases · for labeling professionals
An open question.
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.
Independent development, multiple architectural iterations
A curated corpus of FDA-approved drug labels
Offline research build — no document content leaves the machine