Classification Task Wizard

Description

Lets you specify the tabs to include for classification.

Includes all tabs for classification.

Includes only selected tabs for classification. When you select this option, the available tabs are displayed and you can select the ones you want to classify.

Lets you specify which items to classify from the selected tabs.

Includes all items in selected tabs for classification.

Includes only selected items for classification.

Lets you select the type of sensitive information for classification and set the level of confidence.

Protected health information, also referred to as personal health information, refers to the past, present or future physical or mental health condition of an individual including their medical histories, test and laboratory results, insurance and payment information, and other data that a healthcare professional collects to identify an individual and determine appropriate care.

Payment card information is information related to transactions involving credit cards, prepaid cards, point-of-sale cards, e-purse, bank debit, and ATM cards. Sensitive information may include, credit card account numbers, PIN and CVD (card verification data) numbers, expiration dates, as well as information stored on magnetic strips and chips (data and RFID).

Personally identifiable information is any information about an individual, including (1) any information that can be used to distinguish or trace an individual‘s identity, such as their name, social security number, date and place of birth, mother‘s maiden name, or biometric records; and (2) other information that is linked to an individual, such as medical, educational, financial, and employment records.

The Confidence Threshold is the percentage cut-off that you set for the classification. The higher you set the threshold, the more accurate the results. However, a higher threshold also means that fewer items will be labeled by the classification.It is best to strike a balance between the number of items in your case and the accuracy you need. For this reason, we recommend starting with the default value of 50% and adjusting it over time as you provide additional data to predict, and then integrate it into your workflow.