Adjusting survival curves for imbalances in prognostic factors
1988
Adjusting Survival Curves for Prognostic Factors
publication
Evidence: moderate
Author Information
Author(s): W.M. Gregory
Primary Institution: Clinical Operational Research Unit, University College London
Hypothesis
A new method for comparing the survival of two or more groups of patients adjusting for factors distributed unevenly between the groups is presented.
Conclusion
The new method allows for a more accurate reflection of survival curves by adjusting for time-dependent effects of prognostic factors.
Supporting Evidence
- The method provides a graphical counterpart to Mantel's adjusted chi-square statistic.
- It allows for retrospective stratification for prognostic factors.
- The method can show time-dependent effects of prognostic factors.
- It enhances the evaluation of survival differences in clinical trials.
Takeaway
This study introduces a way to make survival comparisons between patient groups fairer by considering factors that might not be evenly distributed.
Methodology
The method adjusts survival curves at every event based on the number of patients still at risk in each group.
Want to read the original?
Access the complete publication on the publisher's website