Assay Accuracy via ML Image Analysis and Self-Validation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing biological and chemical assays in limited resource settings face challenges in accuracy due to random errors and unpredictable operational conditions, lacking effective methods to ensure the reliability of assay results.

Innovation Solution

The implementation of a method that uses imaging and machine learning algorithms to analyze images of the assay process and sample conditions, generating a trustworthy score to validate the accuracy of assay results by comparing them with training data, and employing monitoring structures within the assay device to monitor operational quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional perfect protocol paradigm is used to ensure assay accuracy, then assay accuracy is improved, but device complexity and operational requirements increase

Engineering Contradiction:

Improveassay accuracyVSAvoidcomplex machines and professional operation

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs self-diagnosis and self-validation by automatically capturing images of the assay process, analyzing operational parameters, and generating trustworthiness scores without requiring external verification or complex intervention equipment

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements continuous feedback loops where assay operational images are captured, analyzed by machine learning algorithms, and used to generate trustworthiness scores that validate whether the assay results are reliable, creating a closed-loop quality control system

Inventive Principle:

Principle #23Feedback

2Measurement precision

If traditional perfect protocol paradigm is used to ensure assay accuracy, then assay accuracy is improved, but ease of operation decreases

Engineering Contradiction:

Improveassay accuracyVSAvoidprofessional operation requirement

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The assay system automatically performs quality control functions by capturing its own operational images and analyzing them through machine learning algorithms, eliminating the need for professional operators to manually verify assay conditions

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces manual professional judgment and operational skills with automated machine learning algorithms that analyze assay images and generate trustworthiness scores, making the system accessible to non-experts

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If monitoring structures are added inside the sample to improve accuracy, then assay reliability is improved, but device complexity increases

Engineering Contradiction:

Improveassay result reliabilityVSAvoidmonitoring structures in sample

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The monitoring structures serve multiple functions simultaneously: they act as spatial references for image analysis, quality control indicators for assay conditions, and validation markers for result trustworthiness, reducing the need for separate dedicated monitoring components

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20230324278A1Assay accuracy improvement

Publication Date: 2023.10.12 ESSENLIX CORP

AI summary

One aspect of the present invention is to provide systems and methods that improve the accuracy of an assay that comprise at least one or more parameters each having a random error.