Machine learning-based prediction model for responses of bDMARDs in patients with rheumatoid arthritis and ankylosing spondylitis

Abstract

Background Few studies on rheumatoid arthritis (RA) have generated machine learning models to predict biologic disease-modifying antirheumatic drugs (bDMARDs) responses; however, these studies included insufficient analysis on important features. Moreover, machine learning is yet to be used to predict bDMARD responses in ankylosing spondylitis (AS). Thus, in this study, machine learning was used to predict such responses in RA and AS patients. Methods Data were retrieved from the Korean College of Rheumatology Biologics therapy (KOBIO) registry. The number of RA and AS patients in the training dataset were 625 and 611, respectively. We prepared independent test datasets that did not participate in any process of generating machine learning models. Baseline clinical characteristics were used as input features. Responders were defined as those who met the ACR 20% improvement response criteria (ACR20) and ASAS 20% improvement response criteria (ASAS20) in RA and AS, respectively, at the first follow-up. Multiple machine learning methods, including random forest (RF-method), were used to generate models to predict bDMARD responses, and we compared them with the logistic regression model. Results The RF-method model had superior prediction performance to logistic regression model (accuracy: 0.726 [95% confidence interval (CI): 0.725–0.730] vs. 0.689 [0.606–0.717], area under curve (AUC) of the receiver operating characteristic curve (ROC) 0.638 [0.576–0.658] vs. 0.565 [0.493–0.605], F1 score 0.841 [0.837–0.843] vs. 0.803 [0.732–0.828], AUC of the precision-recall curve 0.808 [0.763–0.829] vs. 0.754 [0.714–0.789]) with independent test datasets in patients with RA. However, machine learning and logistic regression exhibited similar prediction performance in AS patients. Furthermore, the patient self-reporting scales, which are patient global assessment of disease activity (PtGA) in RA and Bath Ankylosing Spondylitis Functional Index (BASFI) in AS, were revealed as the most important features in both diseases. Conclusions RF-method exhibited superior prediction performance for responses of bDMARDs to a conventional statistical method, i.e., logistic regression, in RA patients. In contrast, despite the comparable size of the dataset, machine learning did not outperform in AS patients. The most important features of both diseases, according to feature importance analysis were patient self-reporting scales.

Development and Validation of a Machine Learning-Based Nomogram for Prediction of Ankylosing Spondylitis

“…The proportion of hs-CRP (Table 4 ) in patients with AS > 10 was significantly higher than that in patients without AS, and the proportion of hs-CRP < 0.8 was lower than that in patients without AS. In a study by Seulkee et al, CRP was higher in patients with symptoms of AS than in patients without symptoms [ 6 ]. WBC and NEUT were elevated in patients with AS, consistent with chronic inflammation.…”

“…It is the intersection of statistics, which learns relationships from data, and computer science, which emphasizes efficient computational algorithms. ML is now widely used in the study of clinically relevant data [ 6 , 7 ]. Liang et al used LASSO regression to find that the platelet-to-lymphocyte ratio could be an independent factor in diagnosing AS [ 8 ].…”

Machine learning predicts response to TNF inhibitors in rheumatoid arthritis: results on the ESPOIR and ABIRISK cohorts

“…The results of this study can be compared with similar initiatives using machine learning to predict treatment response to TNFi. [9][10][11][12] The prediction of the therapeutic response is the most frequent task; however, the only study providing a replication dataset and using the EULAR response as the primary endpoint is the publication of the winners of the DREAM RA Challenge. 9 Their model was developed using genomic data and reached an AUROC of 0.62.…”

“…Using this approach in clinical practice remains a challenge since genetic data are not widely available. Other initiatives11 12 apply machine learning on clinical and biological data for similar objectives. However, these approaches often fail to describe how such models could be useful in clinical practice.…”

Female Sex, Age, and Unfavorable Response to Tumor Necrosis Factor Inhibitors in Patients With Axial Spondyloarthritis: Results of Statistical and Artificial Intelligence–Based Data Analyses of a National Multicenter Prospective Registry

“…Also, the application of AI-based data analyses in addition to statistical methods is original. To the best of our knowledge, no studies in the whole spectrum of the disease (axial SpA) analyzing different lines of TNFi have been published yet, although a machine learning model to predict the treatment responses to the first TNFi in patients with AS has been reported (44).…”