The impact of different censoring methods for analyzing survival using real-world data with linked mortality information: a simulation study.
| Title: | The impact of different censoring methods for analyzing survival using real-world data with linked mortality information: a simulation study. |
|---|---|
| Authors: | Hsu WC; Genesis Research Group, 111 River St, Ste 1120, Hoboken, NJ, 07030, USA.; Crowley A; Genesis Research Group, 111 River St, Ste 1120, Hoboken, NJ, 07030, USA.; Parzynski CS; Genesis Research Group, 111 River St, Ste 1120, Hoboken, NJ, 07030, USA. Craig.Parzynski@genesisrg.com. |
| Source: | BMC medical research methodology [BMC Med Res Methodol] 2024 Sep 13; Vol. 24 (1), pp. 203. Date of Electronic Publication: 2024 Sep 13. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: BioMed Central Country of Publication: England NLM ID: 100968545 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2288 (Electronic) Linking ISSN: 14712288 NLM ISO Abbreviation: BMC Med Res Methodol Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : BioMed Central, [2001- |
| MeSH Terms: | Computer Simulation*; Electronic Health Records/statistics & numerical data ; Mortality/trends ; Humans ; Survival Analysis ; Monte Carlo Method ; Proportional Hazards Models ; Reproducibility of Results |
| Abstract: | Background: Evaluating outcome reliability is critical in real-world evidence studies. Overall survival is a common outcome in these studies; however, its capture in real-world data (RWD) sources is often incomplete and supplemented with linked mortality information from external sources. Conflicting recommendations exist for censoring overall survival in real-world evidence studies. This simulation study aimed to understand the impact of different censoring methods on estimating median survival and log hazard ratios when external mortality information is partially captured.; Methods: We used Monte Carlo simulation to emulate a non-randomized comparative effectiveness study of two treatments with RWD from electronic health records and linked external mortality data. We simulated the time to death, the time to last database activity, and the time to data cutoff. Death events after the last database activity were attributed to linked external mortality data and randomly set to missing to reflect the sensitivity of contemporary real-world data sources. Two censoring schemes were evaluated: (1) censoring at the last activity date and (2) censoring at the end of data availability (data cutoff) without an observed death. We assessed the performance of each method in estimating median survival and log hazard ratios using bias, coverage, variance, and rejection rate under varying amounts of incomplete mortality information and varying treatment effects, length of follow-up, and sample size.; Results: When mortality information was fully captured, median survival estimates were unbiased when censoring at data cutoff and underestimated when censoring at the last activity. When linked mortality information was missing, censoring at the last activity date underestimated the median survival, while censoring at the data cutoff overestimated it. As missing linked mortality information increased, bias decreased when censoring at the last activity date and increased when censoring at data cutoff.; Conclusions: Researchers should consider the completeness of linked external mortality information when choosing how to censor the analysis of overall survival using RWD. Substantial bias in median survival estimates can occur if an inappropriate censoring scheme is selected. We advocate for RWD providers to perform validation studies of their mortality data and publish their findings to inform methodological decisions better.; (© 2024. The Author(s).) |
| References: | BMJ Open. 2019 Feb 27;9(2):e024895. (PMID: 30819708); Ther Innov Regul Sci. 2021 Sep;55(5):1019-1035. (PMID: 34014439); Clin Pharmacol Ther. 2022 Jan;111(1):135-144. (PMID: 34726771); Health Serv Res. 2021 Dec;56(6):1281-1287. (PMID: 33998685); Ther Innov Regul Sci. 2020 Nov;54(6):1436-1443. (PMID: 32514737); JAMA Netw Open. 2020 Nov 2;3(11):e2024406. (PMID: 33170262); Stat Med. 2019 May 20;38(11):2074-2102. (PMID: 30652356); Pharmacoepidemiol Drug Saf. 2022 Jul;31(7):717-720. (PMID: 35471704); N Engl J Med. 2022 May 5;386(18):1680-1682. (PMID: 35485775); Stat Med. 1982 Apr-Jun;1(2):121-9. (PMID: 7187087); Epidemiology. 2019 Nov;30(6):817-824. (PMID: 31393316); J Clin Oncol. 2012 Sep 10;30(26):3297-303. (PMID: 22649133); Am J Epidemiol. 2018 Mar 1;187(3):623-632. (PMID: 29020256); Stat Med. 2011 Feb 20;30(4):356-67. (PMID: 21225898); Clin Pharmacol Ther. 2022 Jan;111(1):122-134. (PMID: 34716990); Clin Pharmacol Ther. 2023 Aug;114(2):325-355. (PMID: 37079433); Pharmacoepidemiol Drug Saf. 2019 May;28(5):572-581. (PMID: 30873729); Front Med (Lausanne). 2021 May 31;8:669509. (PMID: 34136505); Ann Epidemiol. 2018 Oct;28(10):691-696.e3. (PMID: 30057347); J Cancer Policy. 2023 Mar;35:100403. (PMID: 36646208) |
| Contributed Indexing: | Keywords: Bias; Censoring; Estimation; Missing data; Real-world data; Real-world evidence; Simulation; Survival analysis |
| Entry Date(s): | Date Created: 20240913 Date Completed: 20240914 Latest Revision: 20240916 |
| Update Code: | 20260130 |
| PubMed Central ID: | PMC11395225 |
| DOI: | 10.1186/s12874-024-02313-3 |
| PMID: | 39272007 |
| Database: | MEDLINE |
Journal Article