PHI Type

The identify_phi and redact_phi endpoints, along with the Analyze - Web App, now include labels that are broken down by:

PHI Type (phi_type) - the PHI identifier assigned to the text.
Category (category) - the broader PHI category assigned to the text.

"annotations": [
    {
      "labels": {
        "phi_type": {
          "label": "[PATIENT]",
          "score": 1.0
        },
        "category": {
          "label": "[PERSON]"
        }
      },
      "text": "John Doe",
      "span": {
        "start": 9,
        "end": 17
      }
    },

List of PHI Types

The API currently identifies the following types of PHI:

* AGE
* BIOID
* CITY
* COUNTRY
* DATE
* DEVICE
* DOCTOR
* EMAIL

* FAX
* HEALTHPLAN
* HOSPITAL
* IDNUM
* LOCATION-OTHER
* MEDICALRECORD
* ORGANIZATION
* PATIENT

* PHONE
* PROFESSION
* STATE
* STREET
* URL
* USERNAME
* ZIP

Mappings

Current mappings between PHI types and each category are as follows:

Category	PHI Type
CONTACT	EMAIL, FAX, PHONE, USERNAME
DATE	DATE
DEMOGRAPHICS	AGE, PROFESSION
IDENTIFIER	BIOID, DEVICE, HEALTHPLAN, IDNUM, MEDICAL RECORD
INSTITUTION	ORGANIZATION
LOCATION	CITY, COUNTRY, STATE, STREET, ZIP, LOCATION-OTHER
ORGANIZATION	ORGANIZATION
PERSON	DOCTOR, PATIENT
WEBADDRESS	URL