EN | RU
EN | RU

Help Support

Back

Study to find the role of Multi-omics and machine learning in predicting the clinical response to Adalimumab and Etanercept in RA patients

Study to find the role of Multi-omics and machine learning in predicting the clinical response to Adalimumab and Etanercept in RA patients Study to find the role of Multi-omics and machine learning in predicting the clinical response to Adalimumab and Etanercept in RA patients
Study to find the role of Multi-omics and machine learning in predicting the clinical response to Adalimumab and Etanercept in RA patients Study to find the role of Multi-omics and machine learning in predicting the clinical response to Adalimumab and Etanercept in RA patients

The study was done to predict the response before the anti-TNF therapy in RA. It was performed to know the mechanism with which patients react in a different way to anti-TNF treatment in RA.

See All

Key take away

From a recent study it was found out that machine learning models supporting the molecular signatures can precisely calculate the reaction before the adalimumab or etanercept treatment. They can accurately determine the response to Adalimumab and Etanercept therapy in rheumatoid arthritis (RA) patients.

Background

The study was done to predict the response before the anti-TNF therapy in RA. It was performed to know the mechanism with which patients react in a different way to anti-TNF treatment in RA.

Method

The gene expression and DNA methylation profiling on PBMC, CD4+ T cells,  and monocytes from eighty RA patients before the initiation of adalimumab or etanercept therapy was considered.

To estimate the response after six months of therapy, EULAR criteria was used. The methylation analyses and differential expression were done to recognize the response-associated epigenetic and transcriptional signatures. Machine learning models were built with the help of these signatures to calculate the reaction before the administration of anti-TNF treatment. Then, a follow-up study confirmed them.

Result

Transcriptional signatures in adalimumab or etanercept responders were different in PBMCs (peripheral blood mononuclear cell). The TNF signaling pathway was enriched with the genes upregulated in CD4+ T cells of adalimumab responders. The accuracy of 85.9% and 79% was achieved with the help of machine learning models to calculate the response to adalimumab or etanercept, respectively. The models using differentially methylated positions attained the accuracy of 84.7% and 88% for adalimumab or etanercept, respectively. 

Table- Overall accuracy in prediction of response using differentially methylated positions



Conclusion

The machine learning models supporting the molecular signatures could precisely calculate the reaction before the adalimumab or etanercept treatment.

Source:

Arthritis & Rheumatology

Article:

Multi-omics and machine learning accurately predicts clinical response to Adalimumab and Etanercept therapy in patients with rheumatoid arthritis

Authors:

Weiyang Tao et al.

Comments (0)

You want to delete this comment? Please mention comment Invalid Text Content Text Content cannot me more than 1000 Something Went Wrong Cancel Confirm Confirm Delete Hide Replies View Replies View Replies en ru
Try: