Prediction of response of methotrexate in patients with rheumatoid arthritis using serum lipidomics

Mateusz Maciejewski,Daniel Ziemek,Nisha Nair,Caroline Sands,Anne Barton,Stephanie Ling,Matthew R Lewis,Kimme Hyrich,Darren Plant,Suzanne Verstappen

doi:10.1038/s41598-021-86729-7

Abstract

Methotrexate (MTX) is a common first-line treatment for new-onset rheumatoid arthritis (RA). However, MTX is ineffective for 30–40% of patients and there is no way to know which patients might benefit. Here, we built statistical models based on serum lipid levels measured at two time-points (pre-treatment and following 4 weeks on-drug) to investigate if MTX response (by 6 months) could be predicted. Patients about to commence MTX treatment for the first time were selected from the Rheumatoid Arthritis Medication Study (RAMS). Patients were categorised as good or non-responders following 6 months on-drug using EULAR response criteria. Serum lipids were measured using ultra‐performance liquid chromatography–mass spectrometry and supervised machine learning methods (including regularized regression, support vector machine and random forest) were used to predict EULAR response. Models including lipid levels were compared to models including clinical covariates alone. The best performing classifier including lipid levels (assessed at 4 weeks) was constructed using regularized regression (ROC AUC 0.61 ± 0.02). However, the clinical covariate based model outperformed the classifier including lipid levels when either pre- or on-treatment time-points were investigated (ROC AUC 0.68 ± 0.02). Pre- or early-treatment serum lipid profiles are unlikely to inform classification of MTX response by 6 months with performance adequate for use in RA clinical management.

Highlights

Methotrexate (MTX) is a common first-line treatment for new-onset rheumatoid arthritis (RA)
The aim of this study was to determine if future MTX response can be predicted from ultra-performance liquid chromatography–mass spectrometry (UPLC-MS) derived serum lipidomic data by applying state-of-the-art machine learning methods, under robust nested cross-validation
Following quality control (QC), 3,366 features (1060 in negatively-charged mode and 2306 in positive mode) were available for analysis at pre-treatment and 4 weeks from 100 RA patients categorised as good- (GR, n = 50) or non- (NR, n = 50) responders to MTX following 6 months on drug (Table 1)

Summary

Introduction

Methotrexate (MTX) is a common first-line treatment for new-onset rheumatoid arthritis (RA). A positive rheumatoid factor titre, high health assessment questionnaire (HAQ) score, a high number of tender joints and higher depression and anxiety before starting on MTX are predictive of non-response after 6 months on drug. A positive rheumatoid factor titre, high health assessment questionnaire (HAQ) score, a high number of tender joints and higher depression and anxiety before starting on MTX are predictive of non-response after 6 months on drug6 These factors do not predict MTX nonresponse perfectly and it is likely that other disease- or patient-related factors influence treatment outcome. Metabolomics and lipidomics are emergent approaches for studying pathophysiology and patient stratification in RA Such profiling of biofluids from RA patients has the potential to identify disease processes that underpin important clinical outcomes. The aim of this study was to determine if future MTX response can be predicted from ultra-performance liquid chromatography–mass spectrometry (UPLC-MS) derived serum lipidomic data by applying state-of-the-art machine learning methods, under robust nested cross-validation

Objectives

Methods

Results

Conclusion