Interface for Patient-Provider Conversation and Auto-Generation of Note or Summary

Patent metadata

Field	Value
Publication number	US-2019122766-A1
Application number	US-201815988489-A
Country	US
Kind code	A1
Filing date	May 24, 2018
Priority date	Oct 23, 2017
Publication date	Apr 25, 2019
Grant date	—

Abstract

A method for automatically generating a note summarizing a conversation between a patient and a healthcare provider is disclosed. A workstation is provided with a tool for rendering an audio recording of the conversation and a display for displaying a transcript of the audio recording obtained from a speech-to-text engine. The display of the workstation includes first transcript region for display of the transcript and a second note region for simultaneous displaying of elements of a note summarizing the conversation. Words or phrases in the transcript related to medical topics relating to the patient are extracted with the aid of a trained machine learning model. The extracted words or phrases are highlighted in the transcript and displayed in the note region. Links or a mapping between the extracted words or phrases in the note region and the portions of the transcript from which the extracted words or phrases originated are provided whereby the source and accuracy of the extracted words or phrases in the note region can be verified by a user.

First claim

We claim:

1 . A method for automatically generating a note summarizing a conversation between a patient and a healthcare provider, comprising:
providing on a workstation a tool for rendering an audio recording of the conversation; displaying on a display of the workstation (1) in first transcript region a transcript of the recording in substantial real time with the rendering of the audio recording and simultaneously (2) in a second note region a note summarizing the conversation, the note including automatically extracted words or phrases in the transcript related to medical topics relating to the patient, the extraction of the words or phrase performed with the aid of a trained machine learning model; and providing links or a mapping between the extracted words or phrases in the note region and the portions of the transcript from which the extracted words or phrases originated whereby the source and accuracy of the extracted words or phrases in the note region can be verified by a user of the workstation.

2 . The method of claim 1 , wherein the extracted words or phrases are placed into appropriate categories or classifications in the note region such as symptoms, medications, etc.

3 . The method of claim 1 , wherein the speakers are identified in the transcript.

4 . The method of claim 1 , wherein the transcript and note are editable.

5 . The method of claim 1 , wherein the method further comprises the step of automatically generating suggestions of alternative words or phrases for words or phrases in the transcript and tools to approve, reject or provide feedback on the generated suggestions to thereby edit the transcript.

6 . The method of claim 1 , further comprising the step of rendering the note in a prose style.

7 . The method of claim 1 , further comprising the step of rendering the note in the form of a bullet list.

8 . The method of claim 1 , wherein words or phrases in the transcript relating to symptoms or attributes of such symptoms are grouped and classified together within the note.

9 . The method of claim 8 , wherein the note is editable to change classifications and groupings of symptoms and symptom attributes.

10 . The method of claim 5 , further comprising the step of displaying a confidence level for generated suggestions of alternative words or phrases.

11 . The method of claim 1 , further comprising the step of displaying at least one of suggestions of topics to follow-up with the patient, suggestions of clinical problems, suggestions of potential under-documented problems, and suggested billing codes with portions of the transcript displayed which justify the billing codes.

12 . The method of claim 1 , further comprising the step of displaying an emailable or SMS-ready list of patient instructions, including features for editing the list of instructions, adding new instructions from a list of available or suggested instructions, medication changes, or additions from a list generated from the assessment and plan portion of the doctor's notes.

13 . The method of claim 1 , further comprising displaying a minimized icon on a display of an electronic health record screen which, when activated, toggles to the audio recording of the conversation and the transcript thereof.

14 . The method of claim 1 , further comprising displaying on the workstation interface a search tool to search for words or phrases to insert into the note.

15 . The method of claim 1 , further comprising displaying on the workstation interface a smart search tool permitting searching across the transcript and note for words or phrases identical to and equivalent to a word or phrase entered into the smart search tool.

16 . The method of claim 1 , further comprising the step of providing a tool for downloading the transcript and note to the workstation.

17 . The method of claim 14 , wherein the search tool integrates smart phrase or dot phrase search shortcuts present in the electronic health record of the patient.

18 . A system for facilitating automatically generating a note summarizing a conversation between a patient and a healthcare provider, comprising:
a workstation having a tool for rendering an audio recording of the conversation and generating a transcript of the audio recording using a speech-to-text engine; wherein the workstation includes a display having a first transcript region for display of the transcript of the recording and simultaneously a second note region for display of a note summarizing the conversation; wherein the note region displays extracted words or phrases in the transcript related to medical topics relating to the patient, and wherein the extracted words or phrases in the note region are linked or mapped to the portions of the transcript from which the extracted words or phrases originated whereby the source and accuracy of the extracted words or phrases can be verified by a user of the workstation.

19 . The system of claim 18 , wherein the extracted words or phrases are placed into appropriate categories or classifications in the note region such as symptoms, medications, etc.

20 . The system of claim 18 , wherein the transcript further includes an identification of the speakers.

21 . The system of claim 18 , further comprising a trained machine learning model configured to generate suggestions of alternative words or phrases for words or phrases in the transcript and wherein the workstation further includes tools to approve, reject or provide feedback on the generated suggestions to thereby edit the transcript.

22 . The system of claim 18 , wherein the note is generated in a prose style.

23 . The system of claim 18 , wherein the note is generated in the form of a bullet list.

24 . The system of claim 21 , wherein the trained machine learning model generates a confidence level for generated suggestions of alternative words or phrases.

25 . The system of claim 18 , wherein the workstation further is configured to display a minimized icon on a display of an electronic health record screen which, when activated, toggles to the audio recording of the conversation and the transcript thereof.

26 . The system, of claim 18 , workstation is configured to generate a display of a search tool to search for words or phrases to insert into the note.

27 . The system of claim 18 , further comprising a smart search tool permitting searching across the transcript and note for words or phrases identical to and equivalent to a word or phrase entered into the smart search tool.

28 . The system of claim 26 , wherein the search tool integrates smart phrase or dot phrase search shortcuts present in the electronic health record of the patient.

29 . The system of claim 28 , further comprising a microphone for recording the conversation.

Assignees

• Google Llc

Inventors

• Strader Melissa
• Ito William
• Co Christopher
• Chou Katherine
• Rajkomar Alvin
• Rolfe Rebecca

Classifications

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G16H10/60

  for patient-specific data, e.g. for electronic patient records · CPC title

• G06F17/30684

  Physics · mapped topic

• G10L15/00

  Speech recognition (G10L17/00 takes precedence) · CPC title

• G10L2015/088

  Word spotting · CPC title