Top 3 Use Cases of Text Redaction in Healthcare

The US Department of Health and Human Services (“HHS”) issued the Standards for Privacy of Individually Identifiable Health Information (“Privacy Rule”) to protect the health information of patients. This aligns with the requirement of the Health Insurance Portability and Accountability Act of 1996 (“HIPAA”) that governs the use and disclosure of individuals’ health information. Protected Health Information, as it is called, is subject to the Privacy Rule and determines how the health information is used, ensuring its proper protection without hampering access to high-quality healthcare.

With greater digitization in healthcare, patient records are also becoming easily shareable in the digital format with medical providers and other interested parties for compliance and research purposes. This could include third parties such as educational institutions and government departments. The records may also be needed for some legal matters. Further, the digital format also increases the vulnerability of the documents due to hacking and other breaches of security.

Hope you are aware about the Critical Need for Data Security and the Role of Redaction

All life sciences organizations and healthcare professionals have to abide by the HIPAA rules regarding personally identifiable information (PII) and personal health information (PHI) as defined under its patient privacy and security rights and rules. Nearly 18 identifiers fall under these categories and include:

• Person’s name
• Address
• Phone numbers
• Social security number
• Year of birth
• Year of doing a procedure or treatment
• Account numbers or other financial information
• Vehicle information
• Tattoos or piercings
• Biometric information

The laws apply to everyone in the healthcare system in any way, from doctors, nurses, administrators, billing professionals, and even insurance providers. Non-compliance can attract legal action and fines and penalties. Based on whether it was due to a Reasonable Cause or Wilful Neglect and the severity of the negligence, penalties can cost anywhere between $100 and $50,000 per violation (or per record) going up to a maximum of $1.5 million per year. In extreme cases, it could also become a criminal offense resulting in imprisonment.

To prevent this, it is essential that the personal information be masked using text redaction solution.

Redaction refers to the obscuring of sensitive information from documents in any format including PDFs, images, and scanned documents, to ensure confidentiality. Typically, the PHI/PII is blacked out, and, often, it is done manually.

For small volumes, manual redaction may be enough. But as the volumes increase and since there is a great need for accuracy, the manual process can prove to be time-consuming and prone to errors. This can prove inefficient and expensive, as well as affect the reputation of the organization due to legal implications.

Sounds interesting right? Exactly you are at one stop solutions with teX.Ai. Schedule a Demo to explore capabilities and features of our text redaction tool.

Some try rule-based/regular expression-based automation of redaction, but this only has limited success since even a slight change in the structure of the documents can render them ineffective. To overcome this, some organizations outsource the redaction activity, to ensure effective data protection.

Indium Software’s patent-pending text analytics solution, teX.ai, automatically identifies PII and PHI as per the requirements and redacts the data without the need for manual intervention.

The three use cases of teX.ai redaction include:

• Any Format:teX.ai can be used to intuitively identify and redact PII from scanned documents, PDFs, image files, and more without manual intervention using artificial intelligence and machine learning.
• Any Environment: teX.ai can redact documents from any environment, be it on-prem, in the cloud, or even in a hybrid environment.
• Any Volume: Being a flexible and scalable solution, teX.ai can redact PII/PHI from any volume of documents while ensuring accuracy and consistency.

teX.ai^TM enables you to identify and remove words and phrases that match named patterns in text such as bank account numbers, personal identification numbers, email addresses, and so on to be compliant with HIPAA, GDPR, and other regulatory requirements. The use of AI/ ML helps in:

• Reducing manual entries
• Improving the precision when redacting the entries
• Cost reduction
• Improved data protection

Redaction is used to solve business use cases to classify named entities, names, quantities, values, etc. applying different algorithms and libraries such as named entity recognition, Tesseract, LSTM-CRF, and Open CV.

Some of the other differentiating features of teX.ai include it being highly secure, ISO compliant, and adhering to the best industry practices such as being GDPR and OWASP. All data is encrypted and maintained on the client’s server.

Users can monitor processes and improve their efficiency by mitigating nuances using teX.ai’s customizable dashboards and parameters in an interactive dashboard.

teX.ai supports a multitude of languages including English, all Latin languages, Japanese, Mandarin, Thai, Arabic and more.

teX.ai’s Redaction module uses Computer Vision (bounding boxes) and NLP solutions (entity detection using LSTM CRF) to:

• Identify the selected entities
• Redact the selected entities
• Compare the doc with the redacted version for errors in redaction and correcting it

teX.ai is a SaaS product solution from Indium Software, which provides customer-centric, high quality technology solutions delivering business value for Fortune 500 and Global Enterprises. Incepted in 1999, Indium is a ISO 27001 certified company with 1000+ team members, servicing 350+ clients across several domains.

Apart from redaction, teX.ai helps produce structured data, metadata and insights by extracting data from text, summarizing information, and classifying content.

To know more about how teX.ai can help you be HIPAA compliant, contact us now.