Concept Architecture
Concept
Theoretically, Restricted Mean Survival Time (RMST) is the expected survival time accumulated up to a pre-specified time horizon. It represents the average event-free survival experienced by individuals over a finite follow-up period and provides an absolute summary measure of treatment benefit without requiring the proportional hazards assumption. RMST has become an important alternative to hazard ratios in survival analysis and health economic evaluation.
Mathematically, RMST is defined as the area under the survival curve from time zero to a restriction time �. The survival function may be estimated non-parametrically using the Kaplan?Meier estimator or parametrically using fitted survival models. Treatment effects are commonly expressed as the difference or ratio of RMST values between comparison groups.
In practice, RMST is estimated by integrating the observed or modelled survival curve up to a clinically relevant time horizon. It is widely used in oncology, health technology assessment and economic modelling to compare treatments when hazards are non-proportional or when absolute survival gains are preferred over relative measures.
Purpose
Used to quantify average survival over a fixed follow-up period, compare treatment effectiveness without assuming proportional hazards, summarise absolute treatment benefit and support health economic survival modelling.
Mathematical Formulae
Primary Formula
RMST(�) = ??? S(t) dt
Where:
RMST(�) = restricted mean survival time up to time �
S(t) = survival function
� = pre-specified restriction time
Supporting Formulae
Difference in restricted mean survival time:
?RMST = RMST?(�) ? RMST?(�)
Ratio of restricted mean survival times:
RMST Ratio = RMST?(�) / RMST?(�)
Related Mathematical Methods
- Kaplan?Meier estimator
- Numerical integration
- Parametric survival modelling
- Flexible parametric survival modelling
- Cox proportional hazards regression
- Area under the survival curve analysis
Example
Two oncology treatments are compared over a restriction period of five years. Integration of the Kaplan?Meier survival curves gives an RMST of 3.84 years for Treatment A and 3.26 years for Treatment B.
The treatment effect is:
?RMST = 3.84 ? 3.26 = 0.58 years
Treatment A therefore provides an average survival gain of approximately seven months during the five-year follow-up period.
Excel Implementation
| Function | Example Formula | Health Economics Application |
|---|---|---|
| SUMPRODUCT | =SUMPRODUCT((A3:A100-A2:A99),(B2:B99+B3:B100)/2) | Approximates the area under the survival curve using the trapezoidal rule. |
| SUM | =SUM(C2:C100) | Calculates cumulative survival time across intervals. |
| IF | =IF(A2<=$F$1,B2,0) | Restricts calculations to the specified follow-up time �. |
| INDEX | =INDEX(B2:B100,MATCH($F$1,A2:A100,1)) | Retrieves survival estimates at the restriction time. |
VBA (Optional)
VBA can automate numerical integration of survival curves, estimate RMST and compare treatment groups across multiple survival analyses.
Sources
Royston P, Parmar MKB. Restricted mean survival time: an alternative to the hazard ratio for the design and analysis of randomised trials with a time-to-event outcome. BMC Medical Research Methodology. 2013;13:152.
Uno H, Claggett B, Tian L, et al. Moving beyond the hazard ratio in quantifying the between-group difference in survival analysis. Journal of Clinical Oncology. 2014;32(22):2380?2385.
Briggs A, Claxton K, Sculpher M. Decision Modelling for Health Economic Evaluation. Oxford University Press; 2006.
NICE. Health Technology Evaluations: The Manual. National Institute for Health and Care Excellence; 2022.
Related Concepts (3)
Library
Publications
1
NICE DSU Technical Support Document 21: Flexible methods for survival analysis — Rutherford, Lambert, Sweeting, Pennington, Crowther, Abrams & Latimer, TSD 21 ed., 2020 (NICE Decision Support Unit (University of Sheffield))
Guidance extending standard survival analysis to flexible parametric methods — spline-based models, fractional polynomials, mixture and cure models, and relative-survival approaches — for capturing complex hazard functions in economic evaluation.
Frequently Asked Questions (6)
What is restricted mean survival time?
A survival summary measure calculated as the area under the survival curve up to a specified time point, an alternative to the hazard ratio.
Source: Royston & Parmar 2013
Why is mean survival restricted to a time point?
True mean survival is the area under the whole survival curve, but that curve usually extends beyond the observed data and cannot be measured without extrapolation. Restricting the mean to a chosen time point measures the area only up to that point, giving a quantity that can be read directly from the observed curve without projecting into the unknown. The result is the average event-free time over that period, expressed in the same units as survival itself. The restriction keeps it within the data. Royston and Parmar (2011) describe this measure.
Source: Royston & Parmar 2011
How is restricted mean survival time calculated?
Restricted mean survival time is calculated as the area under the survival curve from time zero up to a specified time point, the restriction time. Integrating, or summing, the survival probabilities over that interval gives the average time survived within it. The restriction to a chosen time is used because, with censoring, survival cannot be estimated reliably to infinity, so the area is taken up to a point within the data. It can be computed from the Kaplan-Meier or a fitted survival curve.
Source: Royston & Parmar 2013
Why is restricted mean survival time used as an alternative to the hazard ratio?
Restricted mean survival time is used as an alternative to the hazard ratio because it is directly interpretable as a difference in average survival time and remains valid when hazards are non-proportional, whereas the hazard ratio assumes proportional hazards and can mislead when the effect varies over time. Comparing restricted mean survival times between groups gives the difference in mean survival up to the horizon, a clinically meaningful measure that does not depend on the proportional hazards assumption, making it attractive where that assumption fails.
Source: Latimer 2013
What is the difference in restricted mean survival time?
The difference in restricted mean survival time between two groups is the difference in the areas under their survival curves up to the restriction time, giving the average extra survival time one group gains over the other within that period. It quantifies the treatment effect as a gain in mean survival time, in the same units as time, which is directly interpretable. This measure summarises the benefit without assuming proportional hazards, and it is used to compare groups and to inform economic evaluation.
Source: Royston & Parmar 2013
What are the limitations of restricted mean survival time?
Restricted mean survival time depends on the chosen restriction time, and different horizons give different values, so the choice must be justified and its influence considered. It summarises survival only up to that time, not the full lifetime, so it does not capture longer-term differences, and for lifetime estimates extrapolation is still needed. Estimating it near the end of follow-up, where few remain at risk, is less reliable. These limitations mean the restriction time is chosen carefully and results interpreted accordingly.
Source: Royston & Parmar 2013
Trust Record
Verified by Dr Darrin Baines
British health economist
Professional identity: darrinbaines.org
Verification date: 23 Oct 2025
Content version: 1.0.0
Canonical Identity
- Term code
- HE-EM-SM-073
Stable URI · Machine-readable · Resolvable · CC BY 4.0