Home

Abstractor

Abstractor is a Rails engine gem for deriving discrete data points from narrative text via natural language processing (NLP). 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 from documents. Like other EAV or SPO data models, Abstractor supports the recording of arbitrarily many statements about a subject/entity.

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

Predicate/Attribute: the predicate/attribute is the property of the thing being described. The predicate/attribute can be any trait or aspect of the subject/entity and expresses a relationship between the subject/entity and the object/value. In Abstractor this is most often a clinical observation or finding. For example, histology diagnosis in a pathology report or tumor response criteria in a radiology exam report.

Object/Value: the object/value is the fulfillment of the property in the thing being described. For example, glioblastoma for the histology diagnosis of a pathology report; complete response for tumor response criteria of a radiology exam report.

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.