Atopic Dermatitis Diagnosis via Gut Microbe Feature Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing atopic dermatitis using machine learning models face challenges due to noise in unprocessed samples and biases in bacterial metagenome analysis, leading to degraded performance.
Innovation Solution
A method and apparatus that analyze a mixture of gut-derived substances and gut environment-like compositions to extract microbial data, select microbe-related features using a feature selection algorithm, and train a machine learning model to diagnose atopic dermatitis, focusing on genera from families like Ruminococcaceae, Lactobacillaceae, and Bacteroidaceae.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If bacterial metagenome analysis is performed without special processing, then the analysis process is simple, but large bias among samples occurs and causative agents cannot be accurately derived
Solution Approach 1:
The patent applies preliminary action by performing sample culturing and enrichment before metagenome analysis. This pre-processing step allows beneficial microbes to be selectively amplified and concentrated, creating a more representative sample that reduces bias and improves the accuracy of causative agent identification.
Solution Approach 2:
The patent changes the physical and biological parameters of the sample through culturing conditions (temperature, pH, nutrient composition, incubation time). These parameter changes selectively promote the growth of pathogenic or disease-related microbes while suppressing non-relevant organisms, thereby enhancing the detection accuracy of causative agents.
2Device complexity
If machine learning model is trained using unprocessed samples, then the training process is straightforward, but noise in training data causes significant degradation in model performance
Solution Approach 1:
The patent extracts and removes noise and irrelevant data from the training samples through selective culturing and filtering processes. This purification of training data eliminates misleading information that would otherwise degrade model performance, while maintaining a manageable training process.
Solution Approach 2:
The patent applies local quality by selectively enhancing specific features of the training data through targeted culturing conditions. Different samples receive optimized processing parameters tailored to their specific characteristics, improving the quality of relevant microbial signals while removing noise, thereby enhancing model reliability.
Data Source
AI summary
A method for determining whether atopic dermatitis is present by using a machine learning model may include a process of analyzing a mixture of a gut-derived substance collected from a subject and a gut environment-like composition, a process of extracting multiple microbial data based on an analysis result of the mixture, a process of selecting microbe-related features to be used in the machine learning model from the multiple microbial data based on a predetermined feature selection algorithm, a process of training the machine learning model with the microbe-related features, and a process of inputting, to the trained machine learning model, the microbial data collected from the subject to be tested and determining whether atopic dermatitis is present. The microbe-related features may include the amount of one or more microbes selected from genera included in families, Ruminococcaceae, Lactobacillaceae, Prevotellaceae, Barnesiellaceae, Bacteroidaceae, Lachnospiraceae, and UCG.010.