A Model-Independent Method to Determine Restricted Mean Survival Time in the Analysis of Survival Curves

Messori, Andrea; Damuzzo, Vera; Agnoletto, Laura; Leonardi, Luca; Chiumente, Marco; Mengato, Daniele

doi:10.1007/s42399-019-00199-7

Cited by 18 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The milestone rates were calculated using the Kaplan–Meier estimates. The model-independent values of RMST data were extracted from Kaplan–Meier curves using DigitizeIt Version 2.2 ( ), and the area under the calculated curve was described according to a previously described method ( 12 , 13 ).…”

Section: Methodsmentioning

confidence: 99%

Consideration of Surrogate Endpoints for Overall Survival Associated With First-Line Immunotherapy in Extensive-Stage Small Cell Lung Cancer

Zhang

Cui

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

BackgroundThe combination of immune checkpoint inhibitors (ICIs) and chemotherapy is known to improve overall survival (OS) in patients with extensive-stage small cell lung cancer (ES-SCLC). ICIs have different response patterns and survival kinetics characteristics from those of the traditional chemotherapy. In first-line treatment for ES-SCLC, there is an urgent need for surrogate endpoints for the early and accurate prediction of OS. This study aimed to assess progression-free survival (PFS), milestone OS rate, milestone restricted mean survival time (RMST), overall response rate (ORR), and disease control rate (DCR) as proposed surrogate endpoints for OS in ES-SCLC for first-line immunotherapy trials.MethodsBetween January 1, 2013, and December 2020, published articles on randomized clinical trials of ICIs plus chemotherapy in patients with ES-SCLC as first-line therapy were searched in PubMed. Abstracts from the ESMO, ASCO, and WCLC, reported from 2018 onwards, were also searched. A weighted regression analysis based on the weighted least squares method was performed on log-transformed estimates of treatment effect, and the determination coefficient (R2) was calculated to evaluate the association between treatment effect on the surrogate endpoint and OS.ResultsSeven trials, representing 3,009 patients, were included to make up a total of 16 analyzed arms. The ratio of the 12-month OS milestone rate (r = −0.790, P = 0.011, R2 = 0.717) and 12-month OS milestone RMST (r = 0.798, P = 0.010, R2 = 0.702) was strongly correlated with the hazard ratio (HR) for OS. The strongest association was observed between the ratio of the 24-month OS milestone RMST and the HR for OS (r = 0.922, P = 0.001, R2 = 0.825). No associations were observed between the HR for OS and PFS and the RR for ORR and DCR.ConclusionsThe results suggested a strong correlation among the ratio of OS milestone rates at 12 months, ratios of OS milestone RMSTs at 12 and 24 months, and HR for OS. The results indicate that OS milestone rates and OS milestone RMSTs could be considered surrogate endpoints of OS in future first-line immunotherapy trials for ES-SCLC.

show abstract

Section: Methodsmentioning

confidence: 99%

Consideration of Surrogate Endpoints for Overall Survival Associated With First-Line Immunotherapy in Extensive-Stage Small Cell Lung Cancer

Zhang

Cui

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…However, a simple parametric model may not well fit the complex survival curve often seen in recent IO development. Several methods of estimating RMST are available [ 22 ] and discussed in literature, including direct integration of Kaplan-Meier survival curves, a jackknife method, and the Royston and Parmar’s modelling using a smoothing spline for the log-hazard function, and more recently the trapezoidal rule approach [ 23 ]. Note that KM uses a step hazard rate function.…”

Section: Methodsmentioning

confidence: 99%

Dynamic RMST curves for survival analysis in clinical trials

Liao

Liu

2020

BMC Med Res Methodol

View full text Add to dashboard Cite

Background: The data from immuno-oncology (IO) therapy trials often show delayed effects, cure rate, crossing hazards, or some mixture of these phenomena. Thus, the proportional hazards (PH) assumption is often violated such that the commonly used log-rank test can be very underpowered. In these trials, the conventional hazard ratio for describing the treatment effect may not be a good estimand due to the lack of an easily understandable interpretation. To overcome this challenge, restricted mean survival time (RMST) has been strongly recommended for survival analysis in clinical literature due to its independence of the PH assumption as well as a more clinically meaningful interpretation. The RMST also aligns well with the estimand associated with the analysis from the recommendation in ICH E-9 (R1), and the test/estimation coherency. Currently, the Kaplan Meier (KM) curve is commonly applied to RMST related analyses. Due to some drawbacks of the KM approach such as the limitation in extrapolating to time points beyond the follow-up time, and the large variance at time points with small numbers of events, the RMST may be hindered. Methods: The dynamic RMST curve using a mixture model is proposed in this paper to fully enhance the RMST method for survival analysis in clinical trials. It is constructed that the RMST difference or ratio is computed over a range of values to the restriction time τ which traces out an evolving treatment effect profile over time. Results: This new dynamic RMST curve overcomes the drawbacks from the KM approach. The good performance of this proposal is illustrated through three real examples. Conclusions: The RMST provides a clinically meaningful and easily interpretable measure for survival clinical trials. The proposed dynamic RMST approach provides a useful tool for assessing treatment effect over different time frames for survival clinical trials. This dynamic RMST curve also allows ones for checking whether the follow-up time for a study is long enough to demonstrate a treatment difference. The prediction feature of the dynamic RMST analysis may be used for determining an appropriate time point for an interim analysis, and the data monitoring committee (DMC) can use this evaluation tool for study recommendation.

show abstract

“…Since RMST and area under the survival curve (AUC) are identical parameters, the RMST can be rather easily calculated taking advantage of a model-independent method of pharmacokinetic AUC calculation, 5 that allows for an extreme simplification of the estimation procedure. Recently, this original model-independent method of RMST calculation 6,7 has been employed in patients with different types of cancer. [7][8][9] A technique for estimating the 95% confidence interval (CI) of RMST has also been made available extending the application of RMST in the analyses of survival curves.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, this original model-independent method of RMST calculation 6,7 has been employed in patients with different types of cancer. [7][8][9] A technique for estimating the 95% confidence interval (CI) of RMST has also been made available extending the application of RMST in the analyses of survival curves. 10 Likewise, the appropriate method for determining the statistical significance in the comparison between the RMSTs of two different treatments has been clarified.…”

Section: Introductionmentioning

confidence: 99%

The Restricted Mean Survival Time as a Tool for Ranking Comparative Outcomes in a Narrative Review That Evaluates a Network of Randomised Trials: An Example Based on Pcsk9 Inhibitors

Messori¹,

Bartoli²,

Chiumente³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Evolocumab and alirocumab have been approved based on a randomised trial. We analysed the outcomes reported in the two trials to develop an original framework of comparative assessment that uses the restricted mean survival time (RMST). The objective was to show that, in the context of a narrative review, the RMST can be an efficient though simple tool to make indirect comparisons. For each cohort of patients (13,784 patients given evolocumab, 9,462 given alirocumab, 23,242 controls; results expressed in months of event-free survival), we determined the values of RMST with 95% confidence intervals [CI] (evolocumab: 33.48, 95%CI: 33.45 to 33.50; alirocumab: 33.89, 95%CI: 36.86 to 33.92). These results, along with those of the control groups, were analysed and interpreted narratively. A univariate statistics was conducted; no network meta-analysis was done. The experience presented herein indicates that a framework of evidence assessment focused on RMST is a worthwhile option.

show abstract

A Model-Independent Method to Determine Restricted Mean Survival Time in the Analysis of Survival Curves

Cited by 18 publications

References 7 publications

Consideration of Surrogate Endpoints for Overall Survival Associated With First-Line Immunotherapy in Extensive-Stage Small Cell Lung Cancer

Consideration of Surrogate Endpoints for Overall Survival Associated With First-Line Immunotherapy in Extensive-Stage Small Cell Lung Cancer

Dynamic RMST curves for survival analysis in clinical trials

The Restricted Mean Survival Time as a Tool for Ranking Comparative Outcomes in a Narrative Review That Evaluates a Network of Randomised Trials: An Example Based on Pcsk9 Inhibitors

Contact Info

Product

Resources

About