Automated Bowel Preparation Assessment via Image Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The quality of bowel preparation before colonoscopy is often poor, leading to inadequate visualization of colonic mucosa, longer procedure times, increased risks, and repeated colonoscopies, resulting in unnecessary resource consumption.

Innovation Solution

A device and platform that analyze images of a liquid and rectal samples to determine visual characteristics, using machine learning models to assess bowel cleanliness and biochemical measurements, thereby guiding the consumption of bowel preparation agents and scheduling colonoscopies for optimal preparation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Illumination intensity

If bowel preparation agents are consumed to cleanse the bowel before colonoscopy, then the visualization of colonic mucosa is improved, but the procedure time increases and the quality of bowel preparation is often poor leading to inadequate visualization

Engineering Contradiction:

Improvevisualization qualityVSAvoidprocedure time

Core Design Contradiction:

Illumination intensityVSLoss of time

Solution Approach 1:

The system performs preliminary assessment of bowel preparation quality by analyzing images of rectal samples and liquid characteristics before the colonoscopy procedure. This allows early identification of inadequate preparation, enabling timely intervention such as administering additional bowel preparation agents or rescheduling the procedure, thereby avoiding wasted procedure time and improving visualization quality.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system provides feedback on bowel preparation quality through automated image analysis, comparing actual preparation status against desired criteria. This feedback loop enables clinicians to adjust bowel preparation regimens based on objective measurements, improving the likelihood of achieving adequate visualization while optimizing procedure timing.

Inventive Principle:

Principle #23Feedback

2Reliability

If bowel preparation quality is poor, then the colonization procedure can be completed, but it results in longer procedure times, increased risks, and repeated colonoscopies

Engineering Contradiction:

Improvecolonoscopy completionVSAvoidprocedure efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary assessment of bowel preparation quality before the colonoscopy procedure through automated image analysis of rectal samples. This early detection allows clinicians to take corrective actions such as administering additional bowel preparation agents or rescheduling the procedure, ensuring that only adequately prepared patients undergo colonoscopy, thereby improving procedure efficiency and reducing repeat procedures.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system provides objective feedback on bowel preparation quality through automated image analysis, enabling clinicians to make informed decisions about proceeding with or rescheduling colonoscopy procedures. This feedback mechanism improves the reliability of successful procedure completion while enhancing overall productivity by reducing repeat procedures.

Inventive Principle:

Principle #23Feedback

3Reliability

If repeated colonoscopies are performed due to poor bowel preparation, then the initial procedure can be redone, but it results in unnecessary resource consumption

Engineering Contradiction:

Improvecolonoscopy accuracyVSAvoidresource consumption

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary assessment of bowel preparation quality through automated image analysis before scheduling colonoscopy procedures. By identifying inadequate preparation in advance, the system prevents scheduling procedures that would likely fail, thereby eliminating unnecessary resource consumption associated with repeat colonoscopies while maintaining high accuracy standards for procedure success.

Inventive Principle:

Principle #10Preliminary action

4Measurement precision

If manual assessment of bowel preparation quality is performed, then the process can be completed, but it is time-consuming and subject to human error

Engineering Contradiction:

Improveassessment accuracyVSAvoidassessment time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system replaces manual visual assessment of bowel preparation quality with automated machine learning-based image analysis. This substitution eliminates human subjectivity and error while processing images rapidly, providing objective, consistent measurements of bowel preparation quality without the time consumption associated with manual review by multiple clinicians.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12118725B2Analyzing image data to determine bowel preparation quality

Publication Date: 2024.10.15 JOHNS HOPKINS UNIVERSITY

AI summary

An analyzing platform may obtain a first image of a liquid in a receptacle. The analyzing platform may analyze the first image to determine a first set of visual characteristics concerning the liquid. The analyzing platform may obtain a second image of a rectal sample in the liquid in the receptacle, wherein the rectal sample originated from a bowel of a subject. The analyzing platform may analyze the second image to determine a second set of visual characteristics concerning the rectal sample. The analyzing platform may determine, based on the first set of visual characteristics and the second set of visual characteristics, rectal sample information. The analyzing platform may cause one or more actions to be performed based on the rectal sample information.