IP Library Granted Patent US 11,670,408
Granted Patent B2
US 11,670,408 · App. 16/588,475 · Granted Jun 6, 2023

System and method for review of automated clinical documentation

Inventor: Joel Praveen Pinto (Aachen, DE)
Assignee: Nuance Communications, Inc.
G16H15/00G06F16/7867G16H10/60
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 11,670,408
App. No.
16/588,475
Granted
Jun 6, 2023
Kind
B2
Abstract

A method, computer program product, and computing system for obtaining, by a computing device, encounter information of a patient encounter, wherein the encounter information may include audio encounter information and video encounter information obtained from at least a first encounter participant. A report of the patient encounter may be generated based upon, at least in part, the encounter information. A relative importance of a word in the report may be determined. A portion of the video encounter information that corresponds to the word in the report may be determined. The portion of the video encounter information that corresponds to the word in the report may be stored at a first location, wherein the video encounter information may be stored at a second location remote from the first location.

Claims (32)

1. A computer-implemented method comprising:

obtaining, by a computing device, encounter information of a patient encounter, wherein the encounter information includes audio encounter information and video encounter information obtained from at least a first encounter participant;

generating a report of the patient encounter based upon, at least in part, the encounter information;

determining a relative importance of a word in the report;

determining a portion of the video encounter information that corresponds to the word in the report, wherein determining the portion of the video encounter information that corresponds to the word in the report includes identifying one or more timestamps of one or more conversational turns that corresponds to the word, wherein each conversational turn is an individual input sequence of the audio encounter information from at least the first encounter participant, wherein determining the portion of the video encounter information that corresponds to the word in the report includes identifying the one or more timestamps of the one or more conversational turns associated with the word based upon, at least in part, attention distribution, wherein the attention distribution is a weight distribution indicating the relative importance of the word and each word in an input sequence for an output target sequence to provide a link between the word in the report and the video encounter information; and

storing, at a first location that is based upon determining the relative importance of the word in the report, the portion of the video encounter information that corresponds to the one or more timestamps of one or more conversational turns that corresponds to the word in the report, wherein the video encounter information and the portion of the video encounter information that corresponds to the one or more timestamps of the one or more conversational turns that corresponds to the word in the report is stored at a second location that is geographically remote from the first location.

2. The computer-implemented method of claim 1 wherein determining the relative importance of the word in the report is based upon, at least in part, a keyword.

3. The computer-implemented method of claim 1 wherein determining the relative importance of the word in the report is based upon, at least in part, one of user feedback and fact extraction.

4. The computer-implemented method of claim 1 wherein the portion of the video encounter information is determined based upon, at least in part, the one or more timestamps.

5. The computer-implemented method of claim 4 further comprising preventing display of at least a portion of the portion of the video encounter information based upon, at least in part, the word in the report.

6. The computer-implemented method of claim 1 wherein the portion of the video encounter information is uploaded on a network to the first location.

7. A computer program product residing on a non-transitory computer readable storage medium having a plurality of instructions stored thereon which, when executed across one or more processors, causes at least a portion of the one or more processors to perform operations comprising:

obtaining encounter information of a patient encounter, wherein the encounter information includes audio encounter information and video encounter information obtained from at least a first encounter participant;

generating a report of the patient encounter based upon, at least in part, the encounter information;

determining a relative importance of a word in the report;

determining a portion of the video encounter information that corresponds to the word in the report, wherein determining the portion of the video encounter information that corresponds to the word in the report includes identifying one or more timestamps of one or more conversational turns that corresponds to the word, wherein each conversational turn is an individual input sequence of the audio encounter information from at least the first encounter participant, wherein determining the portion of the video encounter information that corresponds to the word in the report includes identifying the one or more timestamps of the one or more conversational turns associated with the word based upon, at least in part, attention distribution, wherein the attention distribution is a weight distribution indicating the relative importance of the word and each word in an input sequence for an output target sequence to provide a link between the word in the report and the video encounter information; and

storing, at a first location that is based upon determining the relative importance of the word in the report, the portion of the video encounter information that corresponds to the one or more timestamps of one or more conversational turns that corresponds to the word in the report, wherein the video encounter information and the portion of the video encounter information that corresponds to the one or more timestamps of the one or more conversational turns that corresponds to the word in the report is stored at a second location that is geographically remote from the first location.

8. The computer program product of claim 7 wherein determining the relative importance of the word in the report is based upon, at least in part, a keyword.

9. The computer program product of claim 7 wherein determining the relative importance of the word in the report is based upon, at least in part, one of user feedback and fact extraction.

10. The computer program product of claim 7 wherein the portion of the video encounter information is determined based upon, at least in part, the one or more timestamps.

11. The computer program product of claim 10 wherein the operations further comprise preventing display of at least a portion of the portion of the video encounter information based upon, at least in part, the word in the report.

12. The computer program product of claim 7 wherein the portion of the video encounter information is uploaded on a network to the first location.

13. A computing system including one or more processors and one or more memories configured to perform operations comprising:

obtaining encounter information of a patient encounter, wherein the encounter information includes audio encounter information and video encounter information obtained from at least a first encounter participant;

generating a report of the patient encounter based upon, at least in part, the encounter information;

determining a relative importance of a word in the report;

determining a portion of the video encounter information that corresponds to the word in the report, wherein determining the portion of the video encounter information that corresponds to the word in the report includes identifying one or more timestamps of one or more conversational turns that corresponds to the word, wherein each conversational turn is an individual input sequence of the audio encounter information from at least the first encounter participant, wherein determining the portion of the video encounter information that corresponds to the word in the report includes identifying the one or more timestamps of the one or more conversational turns associated with the word based upon, at least in part, attention distribution, wherein the attention distribution is a weight distribution indicating the relative importance of the word and each word in an input sequence for an output target sequence to provide a link between the word in the report and the video encounter information; and

storing, at a first location that is based upon determining the relative importance of the word in the report, the portion of the video encounter information that corresponds to the one or more timestamps of one or more conversational turns that corresponds to the word in the report, wherein the video encounter information and the portion of the video encounter information that corresponds to the one or more timestamps of the one or more conversational turns that corresponds to the word in the report is stored at a second location that is geographically remote from the first location.

14. The computing system of claim 13 wherein determining the relative importance of the word in the report is based upon, at least in part, a keyword.

15. The computing system of claim 13 wherein determining the relative importance of the word in the report is based upon, at least in part, one of user feedback and fact extraction.

16. The computing system of claim 13 wherein the portion of the video encounter information is determined based upon, at least in part, the one or more timestamps.

17. The computing system of claim 16 wherein the operations further comprise preventing display of at least a portion of the portion of the video encounter information based upon, at least in part, the word in the report.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 9, 2023
From: NUANCE COMMUNICATIONS, INC.
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 065533/0389 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 23, 2020
From: PINTO, JOEL PRAVEEN
To: NUANCE COMMUNICATIONS, INC.
Reel/Frame 052197/0489 →
Cited By (2)
US 12,562,283 US 12,665,087