Diagnostic Cue Generation for Medical Report Accuracy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Medical practitioners face challenges in drafting comprehensive and error-free medical reports, particularly when relying on medical imaging datasets, as existing methods lack effective assistance in identifying and incorporating diagnostic cues.

Innovation Solution

A computer-implemented method that determines diagnostic cues using a processing algorithm based on medical imaging datasets and poses these cues to users through a controlled user interface, aiding in the drafting of medical reports by highlighting patient-specific findings and guiding the inclusion of relevant information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If medical practitioners manually draft medical reports based on medical imaging datasets, then the reports can be created with professional medical judgment, but the accuracy and completeness of diagnostic findings may be compromised due to human error and oversight

Engineering Contradiction:
Improveaccuracy of medical reportVSAvoidcomplexity of reporting workflow
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces an automated cue generation system that acts as an intermediary between the medical imaging data and the practitioner's report drafting process. The system processes imaging datasets to automatically generate diagnostic cues and suggestions, which are then presented to the practitioner for review and incorporation into the final report. This intermediary layer enhances accuracy by ensuring comprehensive coverage of diagnostic findings while maintaining workflow simplicity through user-friendly presentation of cues.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If automated processing algorithms are used to analyze medical imaging datasets, then diagnostic accuracy can be improved, but the integration into existing workflow may increase complexity

Engineering Contradiction:
Improvediagnostic finding accuracyVSAvoidworkflow integration ease
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system employs self-service mechanisms where the automated cue generation runs independently in the background, automatically processing medical imaging datasets and generating diagnostic cues without requiring manual intervention. The cues are then automatically integrated into the reporting workflow, presenting themselves to the practitioner when needed. This self-service approach maintains high diagnostic accuracy while minimizing workflow disruption, as the system handles the complex processing autonomously.

Inventive Principle:
Principle #25Self-service

3Loss of information

If comprehensive diagnostic cues are provided to assist report drafting, then the completeness of medical reports improves, but the time required to review and process cues may increase

Engineering Contradiction:
Improvecompleteness of diagnostic informationVSAvoidtime for report drafting
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary actions by automatically generating and organizing diagnostic cues before the practitioner begins drafting the report. The cue generation process runs in advance, analyzing the medical imaging dataset and preparing a comprehensive list of potential diagnostic findings. This preliminary preparation ensures that all relevant diagnostic information is captured and organized, allowing the practitioner to efficiently review and incorporate cues into the report without time-consuming manual analysis during the drafting process.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20230076903A1Cue-based medical reporting assistance
Publication Date: 2023.03.09 SIEMENS HEALTHINEERS AG
  • US20230076903A1 patent drawing
  • US20230076903A1 patent drawing
  • US20230076903A1 patent drawing

AI summary

A computer-implemented method comprises: obtaining a medical imaging dataset of a current examination of a patient; determining, based on the medical imaging dataset, one or more diagnostic cues using a processing algorithm, wherein the one or more diagnostic cues are associated with patient-specific diagnostic findings; and controlling a user interface to pose the one or more diagnostic cues to a user, as part of a workflow for drawing up a current medical report for the current examination.