Skip to content
Michael Gurley edited this page Apr 14, 2015 · 52 revisions

Abstractor

Abstractor is a Rails engine gem for deriving discrete data points from narrative text via natural language processing. The gem includes a user interface to present the abstracted data points for confirmation/revision by a curator.

Abstractor uses a Subject-Predicate-Object (SPO) or Entity-Attribute-Value (EAV) data model to represent data points abstracted and curated against documents. Like other EAV or SPO data models, Abstractor supports the recording of arbitrarily many statements about a subject or entity.

Subject/Entity: the subject/entity can be anything but is most often a clinical narrative document. For example, a pathology report, radiology exam report or clinic encounter progress note. The host application that contains the Abstractor gem is expected to represent the subject or entity as Rails model that exposes its textual content as an instance method.

Predicate/Attribute: the predicate/attribute can be any trait or aspect of the subject/entity and expresses a relationship between the subject and the object or value. For example, histology diagnosis in a pathology report; disease progression in a radiology exam report; or performance status in a clinical encounter progress note.

anything but is most often a clinical narrative document. For example, a pathology report, radiology exam report or clinic encounter progress note.

In many domains (most especially healthcare), important data points are recorded within narrative documents. Often enormous money and time is expended to manually extract these data points from these documents.

Clone this wiki locally