Automated system and method for improving healthcare communication

Patent metadata

Field	Value
Publication number	US-10832803-B2
Application number	US-201715654083-A
Country	US
Kind code	B2
Filing date	Jul 19, 2017
Priority date	Jul 19, 2017
Publication date	Nov 10, 2020
Grant date	Nov 10, 2020

Abstract

Systems, methods and tools for improving healthcare communication between physicians and patients by utilizing audio recordings systems capable of collecting voice data of patient conversations with healthcare providers. The communication system converts the recorded voice data into text using voice to text conversion software, analyzes the voice data using a natural language processor to parse for key words and phrases relating to the patient's health and concerns. Voice data may be additionally analyzed by cognitive analysis systems and machine learning algorithms designed to identify the sentiment that the patient is portraying while discussing the patient's concerns about health-related experiences or symptoms and cross-referenced with social media and other external websites or applications, confirming a patient's sentiment or providing additional key words and phrases unraised by the patient when communicating with the physician.

First claim

What is claimed is:

1. A computer system comprising
a processor;
a memory device coupled to the processor;
a digital audio recording system;
a video recording system having a camera system; and
a computer readable storage device coupled to the processor, wherein the storage device contains program code executable by the processor via the memory device to implement a method for automating healthcare communication comprising the steps of:
detecting, by said processor via said digital audio recording system, audible sounds from a plurality of audio recording devices positioned throughout facilities of a physician;
enabling, by said processor in response to said detecting said audible sounds, recording functionality of said digital audio recording system;
receiving, by the processor in response to said detecting and said enabling, voice data of a patient communicating with various personnel of said facilities recorded by the digital audio recording system from a continuous audio stream;
detecting, by said processor, human voice variables within said voice data;
converting, by the processor, the voice data to text, wherein said converting comprises:
translating an analog wave recorded by a microphone of the digital audio recording system into digital data via execution of an analog-to-digital converter by digitizing speech of the voice data via determined measurements of the analog wave with respect to a series of intervals;
removing unwanted background noise from said digital data; and
separating sounds of said digital data into different bands of frequency;

parsing, by the processor, the text of the voice data for key words, wherein said parsing comprises:
reading, via a specialized scanner component of said computing system, the text being parsed one character, of characters, at a time;
transforming, by a specialized lexer component of said computing system, a stream of characters into a stream of tokens;
reading, by a specialized parser component of said computing system, the stream of tokens;
building a parse tree based on the stream of tokens and in accordance with language rule code; and
identifying, one or more associated key words or phrases associated with a specified frequency of usage;

analyzing, by the processor based on said human voice variables, the voice data for sentiment and stress variables with respect to said specified frequency of usage thereby indicating a heightened stress of the patient;
further analyzing, by the processor, video data of the patient recorded by a video recording system for additional evidence of the sentiment and stress variables further corresponding to the heightened sense of stress of the patient identified in the voice data, wherein said further analyzing comprises:
enabling, by said processor in response to said detecting movement of said patient, recording functionality of said video recording system comprising a plurality of video recording devices positioned throughout said facilities of said physician;
detecting, by said processor via said video recording system, visual cues of body language of said patient communicating with said various personnel of said facilities; and
identifying, tracking, and emphasizing, by said processor based on said visual cues, symptoms and concerns of said patient with respect to an importance to said physician;

ranking, by the processor, the key words as a function of the sentiment and stress variables analyzed with respect to the video data and the voice data;
generating, by the processor, a list corresponding to the ranking of the key words; and
enabling, by said processor, said physician to review said list thereby enabling said physician to initiate communication with said patient for resolving the heightened sense of stress of the patient with respect to medical symptoms.

2. The computer system of claim 1 , wherein the method of automating healthcare communication further comprises the steps of:
retrieving, by the processor, patient data from one or more network accessible data sources; and
further analyzing, by the processor, the sentiment and stress variables indicating the heightened sense of stress of the patient as a function of the patient data retrieved from the one or more network accessible data sources.

3. The computer system of claim 2 , wherein the one or more network accessible data sources is a social media website.

4. The computer system of claim 1 , wherein the list generated by the processor comprises said one or more keywords organized by frequency of the key word within a specified time frame or as a function of a stress level of the patient providing the voice data comprising the key words.

5. A computer program product, comprising a computer readable hardware storage device storing a computer readable program code, the computer readable program code comprising an algorithm that when executed by a computer processor of a computing system implements a method for automating healthcare communication, the method comprising the steps of:
detecting, by said processor via said digital audio recording system, audible sounds from a plurality of audio recording devices positioned throughout facilities of a physician;
enabling, by said processor in response to said detecting said audible sounds, recording functionality of said digital audio recording system;
receiving, by said processor in response to said detecting and said enabling, voice data of a patient communicating with various personnel of said facilities recorded by said digital voice recording system from a continuous audio stream;
detecting, by said processor, human voice variables within said voice data;
converting, by the processor, the voice data to text, wherein said converting comprises:
translating an analog wave recorded by a microphone of the digital audio recording system into digital data via execution of an analog-to-digital converter by digitizing speech of the voice data via determined measurements of the analog wave with respect to a series of intervals; and
removing unwanted background noise from said digital data; and
separating sounds of said digital data into different bands of frequency;

parsing, by the processor, the text of the voice data for key words, wherein said parsing comprises:
reading, via a specialized scanner component of said computing system, the text being parsed one character, of characters, at a time;
transforming, by a specialized lexer component of said computing system, a stream of characters into a stream of tokens;
reading, by a specialized parser component of said computing system, the stream of tokens;
building a parse tree based on the stream of tokens and in accordance with language rule code; and
identifying, one or more associated key words or phrases associated with a specified frequency of usage;

analyzing, by the processor based on said human voice variables, the voice data for sentiment and stress variables with respect to said specified frequency of usage thereby indicating a heightened stress of the patient;
further analyzing, by the processor, video data of the patient recorded by the video recording system for additional evidence of the sentiment and stress variables further corresponding to the heightened sense of stress of the patient identified in the voice data, wherein said further analyzing comprises:
enabling, by said processor in response to said detecting movement of said patient, recording functionality of said video recording system comprising a plurality of video recording devices positioned throughout said facilities of said physician;
detecting, by said processor via said video recording system, visual cues of body language of said patient communicating with said various personnel of said facilities; and
identifying, tracking, and emph

Assignees

• IBM

Inventors

• Bender Michael
• Childress Rhonda L
• Eckert Kim A
• Pham Minh Q

Classifications

• G06Q50/22 Primary

  Social work or social welfare, e.g. community support activities or counselling services · CPC title

• G06F16/68

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06Q10/00

  Administration; Management · CPC title

• G16H50/20

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

• G06F16/00

  Information retrieval; Database structures therefor; File system structures therefor · CPC title