Voice Input Medical Report Data Generation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Healthcare practitioners face inefficiencies and inaccuracies when entering patient information into medical information systems, as existing systems require significant time and are prone to incompleteness and errors due to data being entered after patient encounters.

Innovation Solution

A computer-implemented method and medical information system that uses voice inputs to automatically generate medical report data through speech-to-text conversion, keyword identification, and data field population, reducing the need for manual data entry and enhancing accuracy and completeness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual data entry is used to enter patient information into the medical information system, then data can be recorded in structured format, but it requires significant time and is prone to incompleteness and errors

Engineering Contradiction:

Improveaccuracy of patient informationVSAvoidtime spent on data entry

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs speech-to-text conversion and keyword extraction during the patient encounter itself, rather than requiring post-encounter data entry. The voice input is processed in real-time to populate medical report data fields, eliminating the need for separate manual documentation time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical process of manual keyboard data entry with an automated voice-based system. Speech-to-text conversion technology transforms spoken words into text, which is then processed by keyword identification algorithms to automatically populate structured data fields, substituting manual typing with automated speech processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If data is entered after the patient encounter, then structured data can be recorded, but the data becomes incomplete and inaccurate due to memory decay

Engineering Contradiction:

Improvecompleteness of patient encounter detailsVSAvoiddelayed data entry

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system captures and processes voice inputs during the actual patient encounter, converting speech to text and extracting keywords in real-time. This preliminary action ensures that all clinical details are recorded while still fresh in the practitioner's memory, eliminating information loss due to delayed documentation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The voice input system allows the practitioner to continuously document patient encounter information throughout the interaction without interrupting the clinical flow. The speech-to-text conversion operates continuously, capturing all relevant details as they are spoken, rather than requiring discrete pauses for manual entry.

Inventive Principle:

Principle #20Continuity of useful action

3Productivity

If voice inputs are used to automatically generate medical report data, then data entry time is reduced and accuracy is improved, but the system complexity increases

Engineering Contradiction:

Improvespeed of generating medical report dataVSAvoidcomplexity of speech processing system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system introduces a speech-to-text conversion module as an intermediary between the practitioner's voice input and the medical information system's data fields. This intermediary component handles the complex speech processing, keyword extraction, and data mapping tasks, shielding the user from system complexity while enabling automated documentation.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The voice input system automatically performs speech-to-text conversion, keyword identification, and data field population without requiring manual intervention. The system self-services the documentation task by processing the practitioner's spoken words and automatically structuring the information into the medical report, reducing the need for manual data entry and system configuration.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS8312057B2Methods and system to generate data associated with a medical report using voice inputs

Publication Date: 2012.11.13 GE PRECISION HEALTHCARE LLC

AI summary

Methods and system to generate data associated with a medical report using voice inputs are described herein. In one example implementation, a computer-implemented method to automatically generate data associated with a medical report using voice inputs received during a first encounter includes receiving a voice input from a source and determining an identity of the source. Additionally, the method includes performing a speech-to-text conversion on the voice input to generate a text string representing the voice input and associating the text string with the identity of the source. Further, the example method includes identifying and selecting one or more keywords from the text string. The one or more keywords are associated with one or more data fields. Further still, the method includes populating the one or more data fields with the identified keywords according to values associated with the identified keywords and the identity of the source.