Sold by: John Snow Labs
Deployed on AWS
Free Trial
The PDF Obfuscation Pipeline is a powerful solution for transforming sensitive PDF documents into safe, shareable assets. It enables organizations to unlock the value of clinical data while ensuring strict compliance with HIPAA, GDPR, and institutional privacy standards.
Overview
The PDF Obfuscation Pipeline helps healthcare providers, researchers, and data scientists safely access and use sensitive clinical data without compromising patient privacy by masking PHI information in PDFs. Whether you are training machine learning models, building decision-support tools, or enabling research collaborations, our PDF Obfuscation Pipeline ensures your documents are privacy-compliant, legible, and faithful to their original structure.
Masked entities include HOSPITAL, NAME, PATIENT, ID,MEDICALRECORD, IDNUM, COUNTRY, LOCATION, STREET, STATE, ZIP, CONTACT, PHONE, DATE. The output is a PDF document, similar to the one at the input, but with fake obfuscated text on top of the targeted entities.
IMPORTANT USAGE INFORMATION:
After subscribing to this product and creating a SageMaker endpoint, billing occurs on an HOURLY BASIS for as long as the endpoint is running.
-Charges apply even if the endpoint is idle and not actively processing requests.
-To stop charges, you MUST DELETE the endpoint in your SageMaker console.
-Simply stopping requests will NOT stop billing.
This ensures you are only billed for the time you actively use the service.
Highlights
- **Entity-Level Obfuscation** The pipeline performs targeted obfuscation of sensitive entities such as NAME, PHONE, and more. These entities are replaced by realistic surrogates, preserving the document usability while ensuring no original data leaks. **Customizable Entity Scope** You define what matters. The pipeline allows full customization of which entities to obfuscate or preserve, giving you control over your de-identification strategy.
- **Rendering-Aware Replacement** Replacements are layout-aware. A name John Smith will be replaced with similar-length entity like Mike Burke, ensuring the document remains visually consistent and readable. **Consistent Entity Replacement** If John Smith is replaced by Mike Tyson on page 1, all other instances of John Smith on all pages will be replaced consistently, preserving referential integrity, which is critical for longitudinal or document-linked analysis.
- **Date Shifting Support** You can apply coherent temporal transformations, such as shifting all dates by 2 months, while preserving the internal temporal relationships between events. **Open Evaluation Dataset** We built and released a benchmark dataset to help evaluate document-level de-identification. It includes metrics and examples that showcase what this pipeline can achieve in realistic clinical settings.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 15 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.c5.9xlarge Inference (Batch) Recommended | Model inference on the ml.c5.9xlarge instance type, batch mode | $95.04 |
ml.m4.4xlarge Inference (Real-Time) Recommended | Model inference on the ml.m4.4xlarge instance type, real-time mode | $95.04 |
ml.c5.4xlarge Inference (Batch) | Model inference on the ml.c5.4xlarge instance type, batch mode | $95.04 |
ml.c5.4xlarge Inference (Real-Time) | Model inference on the ml.c5.4xlarge instance type, real-time mode | $95.04 |
ml.c5.9xlarge Inference (Real-Time) | Model inference on the ml.c5.9xlarge instance type, real-time mode | $95.04 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $95.04 |
Dimensions summary
You pay by the hour based on the compute instance you run and the processing mode you choose. Three instance sizes are available: ml.m4.4xlarge, ml.c5.4xlarge, and ml.c5.9xlarge. Larger instances offer more compute for heavier workloads. Each instance comes in two modes. Batch mode processes documents in scheduled groups. Real-time mode handles requests as they arrive. This gives you six combinations of instance size and mode. Your total cost depends on which instance you pick, which mode you use, and how many hours you run it.
Top-of-mind questions for buyers
You pay per host-hour for the instance you run. Charges accrue only while the instance is running and processing. A stopped or terminated instance stops software metering. Underlying AWS resource fees may still apply based on your AWS account setup.
Both meter per running host-hour on the same instance. Batch mode processes documents in scheduled groups, so you can start it, run a job, and stop it. Real-time mode stays available to handle requests as they arrive, so hours accrue while the endpoint runs. Batch suits periodic jobs; real-time suits continuous demand.
Cost scales with running hours, not document count directly. You raise throughput by choosing a larger instance or running longer. The ml.c5.9xlarge offers more compute than the ml.c5.4xlarge or ml.m4.4xlarge for heavier workloads. You can also run batch jobs and stop the instance between runs to limit accrued hours.
www.johnsnowlabs.com
Helpful?
Vendor refund policy
No refunds are possible.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Upgrade underlying JSL libraries to version 6.4.0
Additional details
Inputs
- Summary
Supported Content Types:
- application/octet-stream
- application/pdf
- image/png
- image/jpeg
- image/bmp
- image/tiff
- image/gif
Notes
- Input must be a valid PDF or image file sent as raw bytes.
- Both single-page and multi-page PDFs are supported.
- application/octet-stream is accepted for any supported format — the model detects the file type automatically from the binary content.
- For batch transform jobs, upload each file as a separate S3 object and use SplitType: None with BatchStrategy: SingleRecord to prevent binary splitting.
- Input MIME type
- application/octet-stream, application/pdf, image/png, image/jpeg, image/bmp, image/gif, image/tiff
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/document-obfuscation-multilingual-name-plus/inputs/real-time
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/document-obfuscation-multilingual-name-plus/inputs/batch
Resources
Vendor resources
Support
Vendor support
For any assistance, please reach out to support@johnsnowlabs.com .
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Mask or Obfuscate Personal Health Information (PHI) in English clinical notes.
Transform clinical text into structured data with NLP, extracting entities, assigning statuses, and linking relationships
Mask or Obfuscate Personal Health Information (PHI) in English clinical notes.
This pipeline can extract clinical conditions, and map the clinical conditions to their respective ICD-10-CM codes.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.