Demos
Medical Data De-identification
- Simple process & setup
- Automatically de-identify structured data, unstructured data, documents, PDF files, and images in compliance with HIPAA, GDPR, or custom needs
- Trusted by 5 of 8 Top Pharma Companies
Accuracy:
99.19correctly de-identified sentences
Performance:
2.46hours
to de-identify 500K patient notes.
Peer-Reviewed, State-of-the-Art Accuracy
Can Zero-Shot Commercial APIs Deliver Regulatory-Grade Clinical Text DeIdentification?
Accepted at Text2Story Workshop at ECIR 2025
Beyond Accuracy: Automated De-Identification of Large Real-World Clinical Text Datasets
Machine Learning for Health (ML4H) 2023
Accurate Clinical and Biomedical Named Entity Recognition at Scale
Software Impacts, July 2022
Live Test with Your Medical Data
The Data De-identification Software
Read the blog post “Accurate PHI De-identification”
1
Analyze
- Risk analysis
- Legal requirements review
- HIPAA Safe Harbor, HIPAA Expert Determination
- CCPA
- GDPR pseudoanonymization, GDPR anonymization
- Quality assurance strategy & process
2
Identify
- ID, name, email, patient ID, SSN, credit card, address, birthday, phone, URL, license number
- Physician name, hospital name, profession, employer, affiliation
- Racial or ethnic origin, religion, political or union affiliation, biometric or genetic data, sexual practice or orientation
3
Measure
- Cleanroom AI Platform (on-site)
- Annotation tool
- Active learning
- Accuracy Measurement & agreement processes
- Correct sampling
- Multi-lingual
4
De-identify
We support:
- Tabular (headers, values)
- Text (NER, text matching)
- PDF: Text or Scanned
- Images(OCR & metadata)
- DICOM (OCR & metadata)
So you can:
- Replace (or delete a field)
- Mask (hash identifiers or shift dates)
- Obfuscate (name, locations, organizations)
- Generalize (disease codes, dates, addresses)
5
Monitor
- Ongoing measurement & model improvement
- Missed sensitive data
- Incident response
- GDPR & CCPA requests
- Emergency unblinding
- Audits
De-identificiation Solutions with Full Range of Features
| John Snow Labs’ De-identification solutions | AWS Medical Comprehend | Microsoft Presidio | Google DLP | |
|---|---|---|---|---|
| De-dentification tool | ||||
| End-to-end service | ||||
| Available also as a standalone library | ||||
| Established new state of the art accuracy in peer reviewed publication | ||||
| Real world reference with >99% correctly recognized PHI | ||||
| Scanned PDF | Integrated | Separate service | Separate service | |
| DICOM | Integrated | Separate service | Separate service | |
| Obfuscation | ||||
| Software with Multilingual support | ||||
| Built on big data framework | ||||
| Possible to fine tune standard pre-trained models | ||||
| Data does not leave your premise | ||||
| Works in air gap insulated server with no internet access |
De-identification in Action
De-Identify Unstructured Clinical Text
Automatically identify protected health information up to 23 entities including Patient, Doctor, Hospital, MedicalRecord, IDNum , Location, Profession etc in clinical documents using our pretrained Spark NLP models.
De-identify structured data
Tools to De-identify PHI (Protected Health Information) from structured datasets automatically while enforcing GDPR and HIPAA compliance and maintaining linkage of clinical data across files.
De-identify PDF documents
De-identify PDF documents using HIPAA guidelines by masking PHI information using out of the box Spark NLP and Spark OCR models.
De-identify DICOM documents
De-identify DICOM documents by masking PHI information on the image and by either masking or obfuscating PHI from the metadata.
De-identify PHI in Multiple Languages
This pipeline can be used to de-identify PHI information from English medical texts. The PHI information will be masked and obfuscated in the resulting text.
Consistent Tokenization & Obfuscation
Ensure data clarity, usability, and consistency while prioritizing privacy and security. Protect sensitive information, without hindering data usability or insight extraction.
