Clinical De-identification for Portuguese
This pipeline can be used to Mask or Obfuscate Personal Health Information (PHI) in Portuguese clinical notes.
API AccessPAID
Est. Price
~$12,000/yr est.
Update Frequency
—
Pricing Tiers
1
Regions
—
Quality SignalsB
Freshness
Recently enriched
Complete
63%
API
API Available
Product Overview
Healthcare NLP & Clinical Data Platform$
Offering: A comprehensive suite of NLP-based clinical entity recognition models and structured healthcare datasets for pharmacovigilance, clinical research, and population health analytics.
Best for: Healthcare data scientists and clinical researchers building automated pipelines for medical record de-identification and drug safety monitoring.
Benefits
- Extensive library of pre-trained clinical NLP models
- Multi-language support for clinical de-identification
- High-granularity SDoH and clinical entity extraction
- Cost-effective pricing compared to enterprise-scale healthcare data platforms
Drawbacks
⚠ Limited longitudinal patient journey tracking compared to Komodo Health · ⚠ Requires technical integration via API rather than turnkey dashboard solutionsProduct Intelligence
Value Score
26
quality per $
Try-ability
15
ease of trial
Product Details
Use Cases
Clinical research anonymization | Regulatory compliance reporting | Secondary use of health data | Population health analytics | Pharmaceutical clinical trial data preparation | Medical education and training | Healthcare operational performance benchmarking
Delivery
API
Data Sources
proprietary models
Detected Use Cases
competitive intelligencecompliance regulatoryhealthcare pharma
Pricing Tiers
Vedex estimate
~$12,000/yr est.
PAIDMEDIUM
Add to Data Room
Get an instant price estimate based on your organization profile — seats, usage rights, and contract term.Estimated ~$12,000/yr est.
Request a sample directly from John Snow Labs.
Web Authority
High Authority15 mentions·3 platforms
Academic Papers
13 × 8 pts+80
LinkedIn
1 × 2 pts+2
Blogs & Newsletters
1 × 2 pts+2
Evidence5 sources
Academic Papers
Clinical named entity recognition in the Portuguese language
Named entity recognition (NER) enables the automatic extraction of medical concepts; however, benchmarks for Portuguese remain scarce.
Academic Papers
A Multi-Layered Framework for De-identification of Clinical ...
De-identification in healthcare is the process of removing or masking Protected Health Information (PHI) from clinical texts, such as names, ...
Academic Papers
MedPT: A Massive Medical Question Answering Dataset ...
by FB Färber · 2025 — To address this, we introduce MedPT, the first large-scale, real-world corpus for Brazilian Portuguese, comprising 384,095 authentic question- ...
Data Dictionary
Expected fields and columns in this data product
About Clinical De-identification for Portuguese
Clinical De-identification for Portuguese is an alternative data product offered by John Snow Labs, available on databricks_marketplace. API access is available for programmatic integration. Vedex estimates pricing at roughly $12,000/yr (an estimate, not a vendor-published price).
This pipeline can be used to Mask or Obfuscate Personal Health Information (PHI) in Portuguese clinical notes.
About John Snow Labs
John Snow Labs is a data provider vendor based in Wilmington, Delaware, USA. The model is a powerful tool for extracting SDoH entities from clinical text. It was specifically trained to identify the conditions in which people are born, grow, live, work, and age that impacts th...