Prediction of 3 months MTX non-response (DAS28>3.2) in early rheumatoid arthritis - clinical predictors only
Validated prediction model to identify DMARD-naïve rheumatoid arthritis patients with high risk of insufficient response to MTX (combination) therapy.
Research authors: H.R. Gosselt, M.M.A. Verhoeven, M. Bulatović-Ćalasan, P. M. Welsing, M. C. F. J. de Rotte, F.P.J. Lafeber, M. Hoogendoorn, R. de Jonge
Version: 1.27
  • Public
  • Rheumatology
  • {{ modelType }}
  • Details
  • Validate model
  • Save input
  • Load input
Display
Units

{{section.title}}

Calculate the result

Set more parameters to perform the calculation

Probability of MTX non-response after 3 months of treatment:

{{ resultSubheader }}
{{ chart.title }}
Result interval {{ additionalResult.min }} to {{ additionalResult.max }}

Conditional information

Model performance: 
Data was first stratified splitted into train (n=249) and test set (n=106) followed by 10 - fold stratified cross-validation to tune the hyperparameters to avoid overfitting of the models.

The AUC of ROC curve on the test set was 0.78 (96% CI: 0.69 - 0.87). A cut-off was chosen based on highest possible sensitivity while specificity remained at least above 0.60 with the rationale to correctly identification as many insufficient responders as possible (sensitivity), while maintaining correct classification of sufficient responders (specificity). Corresponding sensitivity and specifity rates were 81% and 60%, with positive and negative predictive values of 67% and 76%.  

{{ file.classification }}
PRO
Note
Notes are only visible in the result download and will not be saved by Evidencio

This model is provided for educational, training and information purposes. It must not be used to support medical decision making, or to provide medical or diagnostic services. Read our full disclaimer.

Underlying models Part of
Comments
Comment
Please enter a comment
Comments are visible to anyone

Model feedback

No feedback yet 1 Comment {{ model.comments.length }} Comments
On {{ comment.created_at }} {{ comment.user.username }} a no longer registered author wrote:
{{ comment.content }}
logo

Please sign in to enable Evidencio print features

In order to use the Evidencio print features, you need to be logged in.
If you don't have an Evidencio Community Account you can create your free personal account at:

https://www.evidencio.com/registration

Printed results - Examples {{ new Date().toLocaleString() }}

Evidencio Community Account Benefits

With an Evidencio Community account you can:

  • Create and publish your own prediction models.
  • Share your prediction models with your colleagues, research group, organization or the world.
  • Review and provide feedback on models that have been shared with you.
  • Validate your models and validate models from other users.
  • Find models based on Title, Keyword, Author, Institute, or MeSH classification.
  • Use and save prediction models and their data.
  • Use patient specific protocols and guidelines based on sequential models and decision trees.
  • Stay up-to-date with new models in your field as they are published.
  • Create your own lists of favorite models and topics.

A personal Evidencio account is free, with no strings attached!
Join us and help create clarity, transparency, and efficiency in the creation, validation, and use of medical prediction models.

Disclaimer: Calculations alone should never dictate patient care, and are no substitute for professional judgement.
Terms & Conditions | Privacy Policy | Disclaimer | Contact | Refuse cookies |
Evidencio v3.31 © 2015 - 2025 Evidencio. All Rights Reserved