公开(公告)号：US20200334381A1

公开(公告)日：2020-10-22

申请号：US16849252

申请日：2020-04-15

Applicant: 3M INNOVATIVE PROPERTIES COMPANY

Inventor： David E. Yarowsky ,  Marc E. Hamburger ,  Octavian Weiser

IPC: G06F21/62 ,  G06N20/00 ,  G06N5/04 ,  G06F40/284 ,  G06F40/166 ,  G06F40/30

Abstract: The present disclosure directs to systems and methods for natural pseudonymization of text. A natural pseudonym has at least one information attribute same as a piece of sensitive text information. The systems and methods can identify sensitive text information, select a natural pseudonym, and modify a data stream of text data by replacing the piece of sensitive text information with the natural pseudonym.

公开(公告)号：US10679738B2

公开(公告)日：2020-06-09

申请号：US15517648

申请日：2015-10-20

Applicant: 3M INNOVATIVE PROPERTIES COMPANY

Inventor： Kavita A. Ganesan ,  Brian J. Stankiewicz ,  David E. Yarowsky ,  Anna N. Rafferty ,  Michael A. Nossal ,  Anthony R. Davis

IPC: G06F17/30 ,  G16H10/60 ,  G16H15/00 ,  G06F19/00

Abstract: This disclosure describes systems, devices, and techniques for identifying sections of medical documents that are suitable for automated medical coding. In one example, a computer-implemented method includes receiving, by one or more processors, the medical document, wherein the medical document comprises a plurality of sections. The method also may include determining, by the one or more processors and via application of a classification model to each section of the plurality of sections, codability indicia for each section of the plurality of sections, wherein the codability indicia represents whether the respective section is suitable for automated medical coding. The method may include outputting, by the one or more processors, the respective codability indicia for each section of the plurality of sections.

公开(公告)号：US20170300635A1

公开(公告)日：2017-10-19

申请号：US15517648

申请日：2015-10-20

Applicant: 3M INNOVATIVE PROPERTIES COMPANY

Inventor： Kavita A. Ganesan ,  Brian J. Stankiewicz ,  David E. Yarowsky ,  Anna N. Rafferty ,  Michael A. Nossal ,  Anthony R. Davis

IPC: G06F19/00

Abstract: This disclosure describes systems, devices, and techniques for identifying sections of medical documents that are suitable for automated medical coding. In one example, a computer-implemented method includes receiving, by one or more processors, the medical document, wherein the medical document comprises a plurality of sections. The method also may include determining, by the one or more processors and via application of a classification model to each section of the plurality of sections, codability indicia for each section of the plurality of sections, wherein the codability indicia represents whether the respective section is suitable for automated medical coding. The method may include outputting, by the one or more processors, the respective codability indicia for each section of the plurality of sections.