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

Jiang, Ziyuan; Li, Jiajin; Kong, Nahyun; Kim, Jeonghyun; Kim, Bongsoo; Lee, Min-Jung; Park, Yoon Mee; Lee, So‐Yeon; Hong, Soo‐Jong; Sul, Jae Hoon

doi:10.1038/s41598-021-04373-7

Cited by 15 publications

(8 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the transcriptomic data for host gene expression, 16S rRNA microbiome and metagenome shotgun data of the intestinal microbiota, Park, J et al employed machine learning to construct a diagnostic model, the AUC of which was 0.715 44 . In a similar manner, AUC of another machine learning diagnostic model based on the transcriptome of gut epithelial colonocytes and gut microbiota data was 0.75 45 . Besides, a diagnostic model developed based on microbiome in serum extracellular vesicle analysis showed high accuracy (AUC=1.00), but without external validation.…”

Section: Discussionmentioning

confidence: 70%

“…As it is unlikely that all the identified DEGs are strongly associated with the occurrence of AD, it is necessary to further extract critical genes from these DEGs, with benefits from both accurate diagnosis and lower classification calculation complexity. Since the Mean Decrease Gini (MDG) method 31 has shown superiority in screening important genes [21][22][23]32 , we leveraged it in the random forest classifier (RFC) to identify critical genes from DEGs.…”

Section: Diagnosis-related Gene Identification With Random Forestmentioning

confidence: 99%

See 1 more Smart Citation

Accurate diagnosis of atopic dermatitis by applying random forest and neural networks with transcriptomic data

Zhou

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Atopic dermatitis (AD) is one of the most common inflammatory skin diseases. But the great heterogeneity of AD makes it difficult to design an accurate diagnostic pipeline based on traditional diagnostic methods. In other words, the AD diagnosis has suffered from an inaccurate bottleneck. Thus, it is necessary to develop a novel and accurate diagnostic model to supplement existing methods. The recent development of advanced gene sequencing technologies enables potential in accurate AD diagnosis. Inspired by this, we developed an accurate AD diagnosis based on transcriptomic data in skin tissue. Using these data of 149 subjects, including AD patients and healthy controls, from Gene Expression Omnibus (GEO) database, we screened differentially expressed genes (DEGs) of AD and identified six critical genes (PPP4R1, SERPINB4, S100A7, S100A9, BTC, and GALNT6) by random forest classifier. In a follow-up study of these genes, we constructed a neural network model (average AUC=0.943) to automatically distinguish subjects with AD from healthy controls. Among these critical genes, we found that PPP4R1 and GALNT6 had never been reported to be associated with AD. Although further replications in other cohorts are needed, our findings suggest that these genes may be developed into useful biomarkers of AD diagnosis and may provide invaluable clues or perspectives for further researches on the pathogenesis of AD.

show abstract

Section: Discussionmentioning

confidence: 70%

Section: Diagnosis-related Gene Identification With Random Forestmentioning

confidence: 99%

Accurate diagnosis of atopic dermatitis by applying random forest and neural networks with transcriptomic data

Zhou

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, these children had increased E. coli , fewer bifidobacteria, bacteroides and lower levels of alpha-diversity ( Arboleya et al, 2016 ). Such findings indicate the importance of intestinal microbial changes in the diagnosis of AD as can be determined using machine learning ( Jiang et al, 2022 ). In that study, data from intestinal epithelial cell transcriptomes and flora were collected from 88 AD patients and 73 healthy controls (the average age of the healthy group was 3 months younger than that of the AD group) and the supervised machine learning pipeline—Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest Classifier (RFC) were constructed as based on 44,608 gene expression probes and 366 species of microorganisms in transcriptome and microbial databases.…”

Section: Ai and Skin Diseases As Related To The Gut-skin Axismentioning

confidence: 97%

“…In that study, 10.3389/fmicb.2023.1112010 Frontiers in Microbiology frontiersin.org data from intestinal epithelial cell transcriptomes and flora were collected from 88 AD patients and 73 healthy controls (the average age of the healthy group was 3 months younger than that of the AD group) and the supervised machine learning pipeline-Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest Classifier (RFC) were constructed as based on 44,608 gene expression probes and 366 species of microorganisms in transcriptome and microbial databases. Fifty microbial characteristic maps as related to AD were screened, including akkermanisia, verrucomicrobia, propionibacterium, and those with the highest F1 scores (high precision 0.70 and recall 0.88), could then be used as AD predictors (Jiang et al, 2022). Finally, results from a literature review have verified that these microbial characteristics are highly correlated with AD, and therefore cannot only be used to predict AD but even distinguish among disease subtypes.…”

Section: Ai and Skin Diseases As Related To The Gut-skin Axismentioning

confidence: 99%

Artificial Intelligence in microbiomes analysis: A review of applications in dermatology

Sun

Niu

et al. 2023

Front. Microbiol.

View full text Add to dashboard Cite

Microorganisms are closely related to skin diseases, and microbiological imbalances or invasions of exogenous pathogens can be a source of various skin diseases. The development and prognosis of such skin diseases are also closely related to the type and composition ratio of microorganisms present. Therefore, through detection of the characteristics and changes in microorganisms, the possibility for diagnosis and prediction of skin diseases can be markedly improved. The abundance of microorganisms and an understanding of the vast amount of biological information associated with these microorganisms has been a formidable task. However, with advances in large-scale sequencing, artificial intelligence (AI)-related machine learning can serve as a means to analyze large-scales of data related to microorganisms along with determinations regarding the type and status of diseases. In this review, we describe some uses of this exciting, new emerging field. In specific, we described the recognition of fungi with convolutional neural networks (CNN), the combined application of microbial genome sequencing and machine learning and applications of AI in the diagnosis of skin diseases as related to the gut-skin axis.

show abstract

“… Li X. et al (2021) used three machine learning models to analyze AI-assisted AD diagnosis and subclassify AD severity by 3D Raster Scanning Photoacoustic Mesoscopy (RSOM) images to extract features from volumetric vascular structures and clinical information. Jiang et al (2022) developed a precise and automatic machine learning classifier on the basis of transcriptomic and microbiota data to predict the risk of AD. This method can accurately distinguish 161 subjects with AD from healthy individuals.…”

Section: Introductionmentioning

confidence: 99%

bSRWPSO-FKNN: A boosted PSO with fuzzy K-nearest neighbor classifier for predicting atopic dermatitis disease

Zhao²,

Xu³

et al. 2023

Front. Neuroinform.

View full text Add to dashboard Cite

IntroductionAtopic dermatitis (AD) is an allergic disease with extreme itching that bothers patients. However, diagnosing AD depends on clinicians’ subjective judgment, which may be missed or misdiagnosed sometimes.MethodsThis paper establishes a medical prediction model for the first time on the basis of the enhanced particle swarm optimization (SRWPSO) algorithm and the fuzzy K-nearest neighbor (FKNN), called bSRWPSO-FKNN, which is practiced on a dataset related to patients with AD. In SRWPSO, the Sobol sequence is introduced into particle swarm optimization (PSO) to make the particle distribution of the initial population more uniform, thus improving the population’s diversity and traversal. At the same time, this study also adds a random replacement strategy and adaptive weight strategy to the population updating process of PSO to overcome the shortcomings of poor convergence accuracy and easily fall into the local optimum of PSO. In bSRWPSO-FKNN, the core of which is to optimize the classification performance of FKNN through binary SRWPSO.ResultsTo prove that the study has scientific significance, this paper first successfully demonstrates the core advantages of SRWPSO in well-known algorithms through benchmark function validation experiments. Secondly, this article demonstrates that the bSRWPSO-FKNN has practical medical significance and effectiveness through nine public and medical datasets.DiscussionThe 10 times 10-fold cross-validation experiments demonstrate that bSRWPSO-FKNN can pick up the key features of AD, including the content of lymphocytes (LY), Cat dander, Milk, Dermatophagoides Pteronyssinus/Farinae, Ragweed, Cod, and Total IgE. Therefore, the established bSRWPSO-FKNN method practically aids in the diagnosis of AD.

show abstract

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

Cited by 15 publications

References 59 publications

Accurate diagnosis of atopic dermatitis by applying random forest and neural networks with transcriptomic data

Accurate diagnosis of atopic dermatitis by applying random forest and neural networks with transcriptomic data

Artificial Intelligence in microbiomes analysis: A review of applications in dermatology

bSRWPSO-FKNN: A boosted PSO with fuzzy K-nearest neighbor classifier for predicting atopic dermatitis disease

Contact Info

Product

Resources

About