IP Library Granted Patent US 11,295,272
Granted Patent B2
US 11,295,272 · App. 16/271,329 · Granted Apr 5, 2022

Automated clinical documentation system and method

Inventors: Daniel Paulino Almendro Barreda (London, GB); Dushyant Sharma (Woburn, MA); Joel Praveen Pinto (Aachen, DE); Uwe Helmut Jost (Groton, MA); Patrick A. Naylor (Reading, GB)
Assignee: NUANCE COMMUNICATIONS, INC.
G06Q10/10G06F3/165G06F40/117G06F40/30G06T7/20G10L15/22G10L15/26G10L15/30G10L25/45G10L25/51G16H10/20G16H10/40G16H10/60G16H15/00G16H50/70H04R1/406H04R3/005G06T2207/30196
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,295,272
App. No.
16/271,329
Granted
Apr 5, 2022
Kind
B2
Abstract

A method, computer program product, and computing system for obtaining encounter information of a patient encounter, wherein the encounter information includes machine vision encounter information; and processing the encounter information to generate an encounter transcript.

Claims (37)

1. A computer-implemented method, executed on a computing device, comprising:

obtaining encounter information of a patient encounter, wherein the encounter information includes machine vision encounter information;

processing the encounter information to identify a speaker within the patient encounter, wherein processing the encounter information to identify the speaker within the patient encounter includes comparing the machine vision encounter information of the encounter information to one or more humanoid models, wherein the one or more humanoid models includes a speaking humanoid model of a first encounter participant and a listening humanoid model of the first encounter participant;

determining that the first encounter participant is speaking using the speaking humanoid model;

steering one or more audio recording beams toward the first encounter participant based upon, at least in part, determining that the first encounter participant is speaking using the speaking humanoid model;

processing the encounter information to generate an encounter transcript;

processing the machine vision encounter information of the encounter information to associate a first portion of the encounter information with the first encounter participant;

assigning a first role to the first encounter participant in the encounter transcript based upon the machine vision encounter information, wherein the first role is one of a medical professional, a patient, and a third party; and

processing at least a portion of the encounter transcript to populate at least a portion of a medical record associated with the patient encounter.

2. The computer-implemented method of claim 1 wherein the encounter information further includes audio encounter information.

3. The computer-implemented method of claim 1 wherein processing the encounter information to generate an encounter transcript includes:

processing the encounter information to compartmentalize the encounter information into a plurality of encounter stages.

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 the encounter information includes machine vision encounter information;

processing the encounter information to identify a speaker within the patient encounter, wherein processing the encounter information to identify the speaker within the patient encounter includes comparing the machine vision encounter information of the encounter information to one or more humanoid models, wherein the one or more humanoid models includes a speaking humanoid model of a first encounter participant and a listening humanoid model of the first encounter participant;

determining that the first encounter participant is speaking using the speaking humanoid model;

steering one or more audio recording beams toward the first encounter participant based upon, at least in part, determining that the first encounter participant is speaking using the speaking humanoid model;

processing the encounter information to generate an encounter transcript;

processing the machine vision encounter information of the encounter information to associate a first portion of the encounter information with the first encounter participant;

assigning a first role to the first encounter participant in the encounter transcript based upon the machine vision encounter information, wherein the first role is one of a medical professional, a patient, and a third party; and

processing at least a portion of the encounter transcript to populate at least a portion of a medical record associated with the patient encounter.

5. The computer program product of claim 4 wherein the encounter information further includes audio encounter information.

6. The computer program product of claim 4 wherein processing the encounter information to generate an encounter transcript includes:

processing the encounter information to compartmentalize the encounter information into a plurality of encounter stages.

7. A computing system including a processor and memory configured to perform operations comprising:

obtaining encounter information of a patient encounter, wherein the encounter information includes machine vision encounter information;

processing the encounter information to identify a speaker within the patient encounter, wherein processing the encounter information to identify the speaker within the patient encounter includes comparing the machine vision encounter information of the encounter information to one or more humanoid models, wherein the one or more humanoid models includes a speaking humanoid model of a first encounter participant and a listening humanoid model of the first encounter participant;

determining that the first encounter participant is speaking using the speaking humanoid model;

steering one or more audio recording beams toward the first encounter participant based upon, at least in part, determining that the first encounter participant is speaking using the speaking humanoid model;

processing the encounter information to generate an encounter transcript;

processing the machine vision encounter information of the encounter information to associate a first portion of the encounter information with the first encounter participant;

assigning a first role to the first encounter participant in the encounter transcript based upon the machine vision encounter information, wherein the first role is one of a medical professional, a patient, and a third party; and

processing at least a portion of the encounter transcript to populate at least a portion of a medical record associated with the patient encounter.

8. The computing system of claim 7 wherein the encounter information further includes audio encounter information.

9. The computing system of claim 7 wherein processing the encounter information to generate an encounter transcript includes:

processing the encounter information to compartmentalize the encounter information into a plurality of encounter stages.

10. The computing system of claim 9 wherein the plurality of encounter stages include at least one of a pre-visit portion, one or more examination portions, and a post-visit portion.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 9, 2023
From: NUANCE COMMUNICATIONS, INC.
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 065532/0152 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 13, 2019
From: BARREDA, DANIEL PAULINO ALMENDRO; SHARMA, DUSHYANT; PINTO, JOEL PRAVEEN; JOST, UWE HELMUT; NAYLOR, PATRICK A
To: NUANCE COMMUNICATIONS, INC.
Reel/Frame 050364/0774 →