Restricted mean survival time as a summary measure of time‐to‐event outcome

Hasegawa, Takahiro; Misawa, Saori; Nakagawa, Shintaro; Tanaka, Shinichi; Tsuji, Takanori; Ugai, Hiroyuki; Wakana, Akira; Yodo, Yasuhide; Tsuchiya, Satoru; Suganami, Hideki; Members, Jpma Task Force

doi:10.1002/pst.2004

Cited by 26 publications

(26 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A potential barrier to selecting an RMST-based test at the design stage would be the need to prespecify τ . 25 Regarding the choice of τ , valuable guidance appears in recent publications. 34,35 As we discussed in the “Introduction” section, choosing a clinically relevant value for τ aids clinical interpretation. Although the choice of τ is indeed a challenge at the design stage, the fact that the RMST always comes with this explicit τ may help better interpret the reported treatment effect.…”

Section: Discussionmentioning

confidence: 99%

Empirical power comparison of statistical tests in contemporary phase III randomized controlled trials with time-to-event outcomes in oncology

2020

View full text Add to dashboard Cite

Background: More than 95% of recent cancer randomized controlled trials used the log-rank test to detect a treatment difference making it the predominant tool for comparing two survival functions. As with other tests, the log-rank test has both advantages and disadvantages. One advantage is that it offers the highest power against proportional hazards differences, which may be a major reason why alternative methods have rarely been employed in practice. The performance of statistical tests has traditionally been investigated both theoretically and numerically for several patterns of difference between two survival functions. However, to the best of our knowledge, there has been no attempt to compare the performance of various statistical tests using empirical data from past oncology randomized controlled trials. So, it is unknown whether the log-rank test offers a meaningful power advantage over alternative testing methods in contemporary cancer randomized controlled trials. Focusing on recently reported phase III cancer randomized controlled trials, we assessed whether the log-rank test gave meaningfully greater power when compared with five alternative testing methods: generalized Wilcoxon, test based on maximum of test statistics from multiple weighted log-rank tests, difference in t-year event rate, and difference in restricted mean survival time with fixed and adaptive [Formula: see text]. Methods: Using manuscripts from cancer randomized controlled trials recently published in high-tier clinical journals, we reconstructed patient-level data for overall survival (69 trials) and progression-free survival (54 trials). For each trial endpoint, we estimated the empirical power of each test. Empirical power was measured as the proportion of trials for which a test would have identified a significant result ( p value < .05). Results: For overall survival, t-year event rate offered the lowest (30.4%) empirical power and restricted mean survival time with fixed [Formula: see text] offered the highest (43.5%). The empirical power of the other types of tests was almost identical (36.2%–37.7%). For progression-free survival, the tests we investigated offered numerically equivalent empirical power (55.6%–61.1%). No single test consistently outperformed any other test. Conclusion: The empirical power assessment with the past cancer randomized controlled trials provided new insights on the performance of statistical tests. Although the log-rank test has been used in almost all trials, our study suggests that the log-rank test is not the only option from an empirical power perspective. Near universal use of the log-rank test is not supported by a meaningful difference in empirical power. Clinical trial investigators could consider alternative methods, beyond the log-rank test, for their primary analysis when designing a cancer randomized controlled trial. Factors other than power (e.g. interpretability of the estimated treatment effect) should garner greater consideration when selecting statistical tests for cancer randomized controlled trials.

show abstract

Section: Discussionmentioning

confidence: 99%

Empirical power comparison of statistical tests in contemporary phase III randomized controlled trials with time-to-event outcomes in oncology

2020

View full text Add to dashboard Cite

show abstract

“…Median time to onset, restricted mean survival time (RMST), and restricted mean survival time lost (RMLT) were calculated from the KM analysis. [ 23 , 24 ] Additionally, the proportional hazard assumption was checked graphically using Schoenfeld residual test and checked by observing survival curves. [ 25 ] To detect a difference between survival probabilities between the group, log-rank test, Gehan generalized Wilcoxon procedure, and Tarone–Ware was used.…”

Section: Methodsmentioning

confidence: 99%

Fast pain relief in exercise-induced acute musculoskeletal pain by turmeric-boswellia formulation: A randomized placebo-controlled double-blinded multicentre study

Rudrappa

Murthy²,

Saklecha

et al. 2022

Medicine

View full text Add to dashboard Cite

Background: Plant extracts with analgesic properties are seldom considered for treatment of acute musculoskeletal pain due to delay in onset of analgesia. Turmeric (Curcuma longa) and boswellia (Boswellia serrata) extracts are well-studied antiinflammatory compounds gaining in popularity and used as an alternative to conventional treatments for musculoskeletal pain. This study analyzed the analgesic effect of a formulation of turmeric and boswellia extracts in sesame oil (Rhuleave-K, TBF) in reducing exercise-induced acute musculoskeletal pain in healthy participants.Methods: In this randomized double-blinded placebo-controlled, single-dose, single-day, multicentre study, a total of 232 participants (TBF n = 116; placebo n = 116) having moderate-to-severe exercise-induced acute musculoskeletal pain were randomized in an allocation concealed 1:1 ratio to receive a single dose of 1000 mg of TBF or placebo. The outcome measures were numerical rating scale (NRS), categorical pain relief scale (PRS), onset of analgesia, and short form of McGill questionnaire (SF-MPQ). NRS and PRS were measured from predose to every 30 minutes interval of postdose up to 6 hours at rest, with movement and applying pressure on the affected part. The onset of analgesia was measured from the time of dosage and censored at 6 hours of postdose. The sum of pain intensity difference (SPID6) and total pain relief (TOTPAR6) at 6 hours was, respectively, analyzed from NRS and PRS scores.Results: TBF showed a significant reduction in pain intensity (SPID6 rest ) with 97.85% improvement in cumulative responder analysis compared with 2.46% in placebo. The onset of pain relief was fast and highly significant in the TBF group with 99% of participants having a mean perceptible pain relief at 68.5 minutes (95% confidence interval, 59.5-77.4) and 96% of participants having a mean meaningful pain relief at 191.6 minutes (95% confidence interval, 176.7-206.4) compared to the placebo group. Highly significant and continuous improvement in pain relief was observed in the TBF group with 93% of participants having ≥ 50% of maximum TOTPAR6 with a number needed to treat of 1.1 at rest. Conclusion:Exercise-induced acute musculoskeletal pain can be effectively relieved by TBF (Rhuleave-K) in about 3 hours signifying its strong analgesic activity.Abbreviations: MPR = meaningful pain relief, MSDs = musculoskeletal disorders, NNT = number needed to treat, NRS = numerical rating scale, PID = pain intensity difference, PPR = perceptible pain relief, RMLT = restricted mean survival time lost, RMST = restricted mean survival time, SDD = smallest detectable difference, SF-MPQ = short form of McGill pain questionnaire, SPID = sum of pain intensity difference, SRM = standardized response mean, TOTPAR = total pain relief.

show abstract

“…We compared unadjusted and adjusted survival curves by calculating the restricted mean survival time (RMST) of each curve to time horizons of 6, 12, 18, and 24 mo, before calculating the differences in RMST between chemotherapy groups to estimate the survival benefit of cisplatin-based regimens over carboplatin-based regimens. RMST represents the area under the survival curve, provides an absolute measure of survival time at a specified time horizon (tau), and is a clinically interpretable summary measure of time-to-event outcomes [10].…”

Section: Statistical Analysesmentioning

confidence: 99%

Overall Survival of Patients Receiving Cisplatin or Carboplatin for Primary Metastatic Urothelial Carcinoma of the Bladder: A Contemporary Dutch Nationwide Cohort Study

Richters

Boormans

Heijden

et al. 2022

European Urology Focus

View full text Add to dashboard Cite

Background: Cisplatin is preferred to carboplatin when treating metastatic urothelial carcinoma of the bladder (mUCB), despite its greater toxicity. Randomised studies underpinning this have been performed in noncontemporary populations with limitations in sample sizes and analyses, affecting their validity in current clinical practice. Objective: To estimate overall survival (OS) and assess the benefit of cisplatin-based regimens over carboplatin-based regimens in a contemporary cohort of patients with mUCB. Design, setting, and participants: A nationwide retrospective cohort study was conducted in patients diagnosed with de novo mUCB in the Netherlands between 2016 and 2019, who underwent first-line treatment with cisplatin-or carboplatin-based chemotherapy, based on the data from the Netherlands Cancer Registry. Outcome measurements and statistical analysis: A propensity model for receiving cisplatin-based chemotherapy based on age, sex, age-adjusted Charlson Comorbidity Index, renal function, performance status, serum haemoglobin, and the presence of visceral and bone metastases was used to produce inverse probability weighting (IPW) per patient. Unadjusted and IPW-adjusted Kaplan-Meier OS curves of both chemotherapy groups were compared by restricted mean survival time (RMST). Results and limitations: Of the 1041 patients with mUCB, 359 received either cisplatin (n = 170; 47%) or carboplatin (n = 189; 53%) as first line. The cisplatin group was younger, had fewer comorbidities, and had better performance status and renal function. The median OS in the cisplatin and carboplatin groups was 13.1 and 11.5 mo, respectively. After IPW adjustment, prognostic factors were balanced between the two chemotherapy groups (standardised differences <0.1), and differences in RMST were <2.0 mo and not statistically significant up to 24 mo. Conclusions: After accounting for all known prognostic factors, we found no significant survival benefit for cisplatin over carboplatin as first-line chemotherapy in mUCB.

show abstract

Restricted mean survival time as a summary measure of time‐to‐event outcome

Cited by 26 publications

References 40 publications

Empirical power comparison of statistical tests in contemporary phase III randomized controlled trials with time-to-event outcomes in oncology

Empirical power comparison of statistical tests in contemporary phase III randomized controlled trials with time-to-event outcomes in oncology

Fast pain relief in exercise-induced acute musculoskeletal pain by turmeric-boswellia formulation: A randomized placebo-controlled double-blinded multicentre study

Overall Survival of Patients Receiving Cisplatin or Carboplatin for Primary Metastatic Urothelial Carcinoma of the Bladder: A Contemporary Dutch Nationwide Cohort Study

Contact Info

Product

Resources

About