Decision curve analysis revisited: overall net benefit, relationships to ROC curve analysis, and application to case-control studies
2011

Revisiting Decision Curve Analysis

Sample size: 4658 publication Evidence: moderate

Author Information

Author(s): Rousson Valentin, Zumbrunn Thomas

Primary Institution: University of Lausanne, Institute for Social and Preventive Medicine

Hypothesis

How can decision curve analysis improve the evaluation of prediction models in clinical settings?

Conclusion

The study presents extensions to decision curve analysis that enhance its interpretation and broaden its application.

Supporting Evidence

  • The overall net benefit combines the net benefits for treated and untreated individuals.
  • Decision curve analysis can be applied to case-control studies with some modifications.
  • The complex model showed a higher net benefit than the simple model across various threshold probabilities.

Takeaway

This study helps doctors decide when to treat patients by showing how useful different prediction models are.

Methodology

The study discusses decision curve analysis and its application to case-control studies, emphasizing the overall net benefit.

Limitations

The choice of threshold probability can be subjective and may vary among clinicians.

Participant Demographics

The study analyzed data from a sample of 4658 individuals from the Framingham Heart Study.

Digital Object Identifier (DOI)

10.1186/1472-6947-11-45

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication