Automated clinical documentation system and method

Patent metadata

Field	Value
Publication number	US-11605448-B2
Application number	US-201816058914-A
Country	US
Kind code	B2
Filing date	Aug 8, 2018
Priority date	Aug 10, 2017
Publication date	Mar 14, 2023
Grant date	Mar 14, 2023

Abstract

A method, computer program product, and computing system for visual diarization of an encounter is executed on a computing device and includes obtaining encounter information of a patient encounter. The encounter information is processed to: associate a first portion of the encounter information with a first encounter participant, and associate at least a second portion of the encounter information with at least a second encounter participant. A visual representation of the encounter information is rendered. A first visual representation of the first portion of the encounter information is rendered that is temporally-aligned with the visual representation of the encounter information. At least a second visual representation of the at least a second portion of the encounter information is rendered that is temporally-aligned with the visual representation of the encounter information.

First claim

What is claimed is:

1. A computer-implemented method for visual diarization of an encounter, executed on a computing device, comprising:
obtaining encounter information of a patient encounter, wherein obtaining the encounter information includes one of utilizing a virtual assistant to audibly prompt a patient to provide at least a portion of the encounter information during a pre-visit portion of the patient encounter and utilizing the virtual assistant to audibly prompt the patient to provide at least a portion of the encounter information during a post-visit portion of the patient encounter, wherein the encounter information includes at least one of audio encounter information obtained from the virtual assistant via one or more audio sensors and machine vision encounter information obtained from the virtual assistant via one or more machine vision systems;
processing the encounter information to:
associate a first portion of the encounter information with a first encounter participant, wherein the first portion of the encounter information includes a first portion of the at least one of audio encounter information obtained via the one or more audio sensors and the machine vision encounter information obtained via the one or more machine vision systems, and wherein the first encounter participant is a medical professional, and
associate at least a second portion of the encounter information with at least a second encounter participant, wherein the second portion of the encounter information includes a second portion of the at least one of audio encounter information obtained from the virtual assistant via the one or more audio sensors and the machine vision encounter information obtained from the virtual assistant via the one or more machine vision systems, wherein at least the second encounter participant is the patient;

rendering a visual representation of the encounter information obtained via the one or more audio sensors and the machine vision encounter information obtained via the one or more machine vision systems, wherein the visual representation of the encounter information includes the machine vision encounter information;
rendering a first visual representation of the first portion of the encounter information that is temporally-aligned with the visual representation of the encounter information, wherein rendering of the first visual representation is filtered based upon, at least in part, a selection on a user interface with playback controls displaying the encounter information by a user of the first portion of the at least one of audio encounter information obtained via the one or more audio sensors and the machine vision encounter information obtained via the one or more machine vision systems; and
rendering at least a second visual representation of the at least the second portion of the encounter information that is temporally-aligned with the visual representation of the encounter information, wherein rendering of the at least the second visual representation is filtered based upon, at least in part, a selection on the user interface with the playback controls displaying the encounter information by the user, wherein the selection by the user on the user interface with playback controls is a selection of the second visual representation of the second portion of the at least one of audio encounter information obtained from the virtual assistant via the one or more audio sensors and the machine vision encounter information obtained from the virtual assistant via the one or more machine vision systems, wherein filtering includes visually annotating the visual representation of one of the first and second visual representations indicating whether the encounter information in the encounter transcript is one of the pre-visit portion of the patient encounter and the post-visit portion of the patient encounter.

2. The computer-implemented method of claim 1 further comprising:
generating an encounter transcript based, at least in part, upon the first portion of the encounter information and the at least the second portion of the encounter information.

3. The computer-implemented method of claim 1 wherein the one or more machine vision systems includes one or more of:
an RGB imaging system;
an infrared imaging system;
an ultraviolet imaging system;
a laser imaging system;
an X-ray imaging system;
a SONAR imaging system;
a RADAR imaging system; and
a thermal imaging system.

4. A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:
obtaining encounter information of a patient encounter, wherein obtaining the encounter information includes one of utilizing a virtual assistant to audibly prompt a patient to provide at least a portion of the encounter information during a pre-visit portion of the patient encounter and utilizing the virtual assistant to audibly prompt the patient to provide at least a portion of the encounter information during a post-visit portion of the patient encounter, wherein the encounter information includes at least one of audio encounter information obtained from the virtual assistant via one or more audio sensors and machine vision encounter information obtained from the virtual assistant via one or more machine vision systems;
processing the encounter information to:
associate a first portion of the encounter information with a first encounter participant, wherein the first portion of the encounter information includes a first portion of the at least one of audio encounter information obtained via the one or more audio sensors and the machine vision encounter information obtained via the one or more machine vision systems, and wherein the first encounter participant is a medical professional, and
associate at least a second portion of the encounter information with at least a second encounter participant, wherein the second portion of the encounter information includes a second portion of the at least one of audio encounter information obtained from the virtual assistant via the one or more audio sensors and the machine vision encounter information obtained from the virtual assistant via the one or more machine vision systems, wherein at least the second encounter participant is the patient;

rendering a visual representation of the encounter information obtained via the one or more audio sensors and the machine vision encounter information obtained via the one or more machine vision systems, wherein the visual representation of the encounter information includes the machine vision encounter information;
rendering a first visual representation of the first portion of the encounter information that is temporally-aligned with the visual representation of the encounter information, wherein rendering of the first visual representation is filtered based upon, at least in part, a selection on a user interface with playback controls displaying the encounter information by a user of the first portion of the at least one of audio encounter information obtained via the one or more audio sensors and the machine vision encounter information obtained via the one or more machine vision systems; and
rendering at least a second visual representation of the at least the second portion of the encounter information that is temporally-aligned with the visual representation of the encounter information, wherein rendering of the at least the second visual representation is filtered based upon, at least in part, a selection on the user interface with the playback controls displaying the encounter information by the user, wherein the selection by the user on the user interface with playback controls is a selection of the second visual representation o

Assignees

• Nuance Communications Inc

Inventors

• Owen Donald E
• Erskine Garret N
• Öz Mehmet Mert
• Almendro Barreda Daniel Paulino

Classifications

• G16Y20/00

  Information sensed or collected by the things · CPC title

• G06F16/685

  using automatically derived transcript of audio data, e.g. lyrics (speech recognition G10L15/00) · CPC title

• G06N20/00

  Machine learning · CPC title

• G06T2207/10044

  Radar image · CPC title

• G10L17/00

  Speaker identification or verification techniques · CPC title