Early and Accurate Prediction of Clinical Response to Methotrexate Treatment in Juvenile Idiopathic Arthritis Using Machine Learning

Abstract

Background and Aims: Accurately predicting the response to methotrexate (MTX) in juvenile idiopathic arthritis (JIA) patients before administration is the key point to improve the treatment outcome. However, no simple and reliable prediction model has been identified. Here, we aimed to develop and validate predictive models for the MTX response to JIA using machine learning based on electronic medical record (EMR) before and after administering MTX.Materials and Methods: Data of 362 JIA patients with MTX mono-therapy were retrospectively collected from EMR between January 2008 and October 2018. DAS44/ESR-3 simplified standard was used to evaluate the MTX response. Extreme gradient boosting (XGBoost), support vector machine (SVM), random forest (RF), and logistic regression (LR) algorithms were applied to develop and validate models with 5-fold cross-validation on the randomly split training and test set. Data of 13 patients additionally collected were used for external validation.Results: The XGBoost screened out the optimal 10 pre-administration features and 6 mix-variables. The XGBoost established the best model based on the 10 pre-administration variables. The performances were accuracy 91.78%, sensitivity 90.70%, specificity 93.33%, AUC 97.00%, respectively. Similarly, the XGBoost developed a better model based on the 6 mix-variables, whose performances were accuracy 94.52%, sensitivity 95.35%, specificity 93.33%, AUC 99.00%, respectively.Conclusion: Based on common EMR data, we developed two MTX response predictive models with excellent performance in JIA using machine learning. These models can predict the MTX efficacy early and accurately, which provides powerful decision support for doctors to make or adjust therapeutic scheme before or after treatment.

Personalized prediction of delayed graft function for recipients of deceased donor kidney transplants with machine learning

“…Likewise, XGB is an ensemble learning method, which assembles decision trees as its building blocks to build a strong learner that is able to learn nonlinear relationships between predictors and outcome 35 . XGB has recently been shown to have superior predictive performance to other ML algorithms in various contexts 36 – 39 .…”

Early Prediction of Clinical Response to Etanercept Treatment in Juvenile Idiopathic Arthritis Using Machine Learning

“…Therefore, it is more efficient to explore the correlation between clinical variables and drug efficacy or predict drug efficacy through the trained models. In our previous study, we first established a model to predict the efficacy of methotrexate in JIA using machine learning (Mo et al, 2019). Also, there have already been prediction models generated by multiple machine learning methods for the efficacy of etanercept in psoriasis and ankylosing spondylitis (Liu et al, 2019;Tomalin et al, 2019).…”

“…Due to few patients of external validation, those non-responders could not be well validated temporarily. Additionally, some studies found that mixture modeling with pre-and post-administration variables could significantly improve the predictive performance of the model (Mo et al, 2019;Tomalin et al, 2019). Therefore, we intend to further generate models with variables after administration.…”

XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord Injury

“…[10][11][12][13][14] Among different machine learning systems, extreme gradient boosting (XGBoost) is widely used to accomplish state-of-the-art analyses in diverse fields with good accuracy or area under the receiver operating characteristic curve (AUC). 15,16 XGBoost, a decision-tree-based ensemble machine learning algorithm with a gradient boosting framework, was developed by Chen and Guestrin. 17 It has since been used in traffic census and the field of energy consumption.…”