Accurate diagnosis of atopic dermatitis by combining transcriptome and microbiota data with supervised machine learning

Atopic dermatitis (AD) is a common skin disease in childhood whose diagnosis requires expertise in dermatology. Recent studies have indicated that host genes–microbial interactions in the gut contribute to human diseases including AD. We sought to develop an accurate and automated pipeline for AD di...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2022-01, Vol.12 (1), p.290-290, Article 290
Main Authors: Jiang, Ziyuan, Li, Jiajin, Kong, Nahyun, Kim, Jeong-Hyun, Kim, Bong-Soo, Lee, Min-Jung, Park, Yoon Mee, Lee, So-Yeon, Hong, Soo-Jong, Sul, Jae Hoon
Format: Article
Language:English
Subjects:
631/114/1305
631/114/2413
631/208/514/1949
631/326/2565/2134
631/326/41/2142
692/53/2421
692/53/2423
692/699/4033
Atopic dermatitis
Case-Control Studies
Children
Colon - metabolism
Colon - microbiology
Dermatitis
Dermatitis, Atopic - diagnosis
Dermatitis, Atopic - genetics
Dermatitis, Atopic - microbiology
Diagnosis
Diagnosis, Computer-Assisted
Dysbiosis
Eczema
Female
Gastrointestinal Microbiome
Gene Expression Profiling
Host-Pathogen Interactions
Humanities and Social Sciences
Humans
Infant
Learning algorithms
Machine learning
Male
Microbiota
Microorganisms
multidisciplinary
Predictive Value of Tests
Science
Science (multidisciplinary)
Skin diseases
Supervised Machine Learning
Transcriptome
Transcriptomes
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Atopic dermatitis (AD) is a common skin disease in childhood whose diagnosis requires expertise in dermatology. Recent studies have indicated that host genes–microbial interactions in the gut contribute to human diseases including AD. We sought to develop an accurate and automated pipeline for AD diagnosis based on transcriptome and microbiota data. Using these data of 161 subjects including AD patients and healthy controls, we trained a machine learning classifier to predict the risk of AD. We found that the classifier could accurately differentiate subjects with AD and healthy individuals based on the omics data with an average F1-score of 0.84. With this classifier, we also identified a set of 35 genes and 50 microbiota features that are predictive for AD. Among the selected features, we discovered at least three genes and three microorganisms directly or indirectly associated with AD. Although further replications in other cohorts are needed, our findings suggest that these genes and microbiota features may provide novel biological insights and may be developed into useful biomarkers of AD prediction.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-021-04373-7