1. Home
  2. Docs
  3. Philter
  4. Introduction
  5. PHI and PII

PHI and PII

PHI, or Protected Health Information, is a collection of personally identifiable health information. The types of PII (personally identifiable information) and PHI detected by Philter is configurable.

What is PHI?

The Health Insurance Portability And Accountability Act (HIPAA) defines 18 types of PHI:

  1. Names (Full or last name and initial)
  2. All geographical identifiers smaller than a state, except for the initial three digits of a zip code if, according to the current publicly available data from the U.S. Bureau of the Census: the geographic unit formed by combining all zip codes with the same three initial digits contains more than 20,000 people; and the initial three digits of a zip code for all such geographic units containing 20,000 or fewer people is changed to 000
  3. Dates (other than year) directly related to an individual
  4. Phone Numbers
  5. Fax numbers
  6. Email addresses
  7. Social Security numbers
  8. Medical record numbers
  9. Health insurance beneficiary numbers
  10. Account numbers
  11. Certificate/license numbers
  12. Vehicle identifiers (including serial numbers and license plate numbers)
  13. Device identifiers and serial numbers;
  14. Web Uniform Resource Locators (URLs)
  15. Internet Protocol (IP) address numbers
  16. Biometric identifiers, including finger, retinal and voice prints
  17. Full face photographic images and any comparable images
  18. Any other unique identifying number, characteristic, or code except the unique code assigned by the investigator to code the data

Philter and PHI

Because Philter only operates on clinical text, the biometric identifiers and face images are not applicable to Philter. For the remaining 16 types, let’s look at how Philter handles each one.

Names

Philter can detect names in natural language text using machine learning algorithms.

Geographic identifiers

Philter can detect many US cities, all US counties, and all US states (full names and abbreviations).

Dates

Philter can detect dates in many formats such as with hypens (10-10-2000), with slashes (10/10/2000), or spelled out (May 1, 2000).

Phone and Fax Numbers

Philter can detect phone (and fax) numbers in many formats. Philter is currently limited to US numbers.

Email addresses

Philter can detect email addresses per the email standard (summarized on Wikipedia).

Social Security numbers

Philter can detect social security numbers (SSNs) in multiple formats such as with spaces and hyphens.

Medical record numbers

Philter can identify unique alphanumeric identifiers.

Health insurance beneficiary numbers

Philter can identify unique alphanumeric identifiers.

Account numbers

Philter can identify unique alphanumeric identifiers.

Certificate/license numbers

Philter can identify unique alphanumeric identifiers.

Vehicle identifiers

Philter can identify vehicle serial numbers (VIN numbers).

Device identifiers and serial numbers

Philter can identify unique alphanumeric identifiers.

Web Uniform Resource Locators (URLs)

Philter can identify URLs adhering to the URL naming standard.

Internet Protocol (IP) address numbers

Philter can identify IPv4 (such as 127.0.0.1) and IPv6 (such as 2001:0db8:85a3:0000:0000:8a2e:0370:7334) addresses.

Any other unique identifying number, characteristic, or code

Philter can identify other unique alphanumeric identifiers.

Back to Philter.

Was this article helpful to you? Yes No

How can we help?