Assessing delayed treatment benefits of immunotherapy using long-term average hazard: a novel test/estimation approach

Miki Horiguchi, Lu Tian, Kenneth L. Kehl and Hajime Uno ()
Additional contact information
Miki Horiguchi: Dana-Farber Cancer Institute
Lu Tian: Stanford University
Kenneth L. Kehl: Dana-Farber Cancer Institute
Hajime Uno: Dana-Farber Cancer Institute

Lifetime Data Analysis: An International Journal Devoted to Statistical Methods and Applications for Time-to-Event Data, 2025, vol. 31, issue 4, No 3, 784-809

Abstract: Abstract Delayed treatment effects on time-to-event outcomes are commonly observed in randomized controlled trials of cancer immunotherapies. When the treatment effect has a delayed onset, the conventional test/estimation approach—using the log-rank test for between-group comparison and Cox’s hazard ratio to quantify the treatment effect—can be suboptimal. The log-rank test may lack power in such scenarios, and the interpretation of the hazard ratio is often ambiguous. Recently, alternative test/estimation approaches have been proposed to address these limitations. One such approach is based on long-term restricted mean survival time (LT-RMST), while another is based on average hazard with survival weight (AH-SW). This paper integrates these two concepts and introduces a novel long-term average hazard (LT-AH) approach with survival weight for both hypothesis testing and estimation. Numerical studies highlight specific scenarios where the proposed LT-AH method achieves higher power than the existing alternatives. The LT-AH for each group can be estimated nonparametrically, and the proposed between-group comparison maintains test/estimation coherency. Because the difference and ratio of LT-AH do not rely on model assumptions about the relationship between two groups, the LT-AH approach provides a robust framework for estimating the magnitude of between-group differences. Furthermore, LT-AH allows for treatment effect quantification in both absolute (difference in LT-AH) and relative (ratio of LT-AH) terms, aligning with guideline recommendations and addressing practical needs. Given its interpretability and improved power in certain settings, the proposed LT-AH approach offers a useful alternative to conventional hazard-based methods, particularly when delayed treatment effects are expected.

Keywords: Average intensity; General censoring-free incidence rate; Immunotherapy; Non-proportional hazards; Restricted mean survival time; T-year event rate (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10985-025-09671-0 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lifeda:v:31:y:2025:i:4:d:10.1007_s10985-025-09671-0

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10985

DOI: 10.1007/s10985-025-09671-0

Access Statistics for this article

Lifetime Data Analysis: An International Journal Devoted to Statistical Methods and Applications for Time-to-Event Data is currently edited by Mei-Ling Ting Lee

More articles in Lifetime Data Analysis: An International Journal Devoted to Statistical Methods and Applications for Time-to-Event Data from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().