Figure - available from: Arthritis Research & Therapy
This content is subject to copyright. Terms and conditions apply.
SHAP summary plots/impact of variables on model outcome. Variables are sorted in descending order of impact. Positive SHAP values indicate an effect in the direction of higher risk of ineffectiveness. Correspondingly, negative values indicate an effect of the factor in the direction of a lower risk for ineffectiveness. High values for the variables (features) are encoded in red; correspondingly low values are encoded in blue

SHAP summary plots/impact of variables on model outcome. Variables are sorted in descending order of impact. Positive SHAP values indicate an effect in the direction of higher risk of ineffectiveness. Correspondingly, negative values indicate an effect of the factor in the direction of a lower risk for ineffectiveness. High values for the variables (features) are encoded in red; correspondingly low values are encoded in blue

Source publication
Article
Full-text available
Objectives Machine learning models can support an individualized approach in the choice of bDMARDs. We developed prediction models for 5 different bDMARDs using machine learning methods based on patient data derived from the Austrian Biologics Registry (BioReg). Methods Data from 1397 patients and 19 variables with at least 100 treat-to-target (t2...

Citations

... This can lead to improved model performance, especially in the context of highly imbalanced datasets, where traditional classifiers may bias towards the majority class. The effectiveness of SMOTE in addressing class imbalance has been welldocumented in previous studies [39,41]. ...
... AUC, F1 score, and G-means are the three comprehensive metrics we prioritize in model evaluation. Specifically, we considered a value above 0.7 for these metrics as indicative of good model performance [41]. In summary, the combination of these metrics provides a comprehensive understanding of model performance, helping to assess its accuracy and applicability. ...
Article
Full-text available
Objective To use routine demographic and clinical data to develop an interpretable individual-level machine learning (ML) model to diagnose knee osteoarthritis (KOA) and to identify highly ranked features. Methods In this retrospective, population-based cohort study, anonymized questionnaire data was retrieved from the Wu Chuan KOA Study, Inner Mongolia, China. After feature selections, participants were divided in a 7:3 ratio into training and test sets. Class balancing was applied to the training set for data augmentation. Four ML classifiers were compared by cross-validation within the training set and their performance was further analyzed with an unseen test set. Classifications were evaluated using sensitivity, specificity, positive predictive value, negative predictive value, accuracy, area under the curve(AUC), G-means, and F1 scores. The best model was explained using Shapley values to extract highly ranked features. Results A total of 1188 participants were investigated in this study, among whom 26.3% were diagnosed with KOA. Comparatively, XGBoost with Boruta exhibited the highest classification performance among the four models, with an AUC of 0.758, G-means of 0.800, and F1 scores of 0.703. The SHAP method reveals the top 17 features of KOA according to the importance ranking, and the average of the experience of joint pain was recognized as the most important features. Conclusions Our study highlights the usefulness of machine learning in unveiling important factors that influence the diagnosis of KOA to guide new prevention strategies. Further work is needed to validate this approach.