TY - JOUR
T1 - Comparing Modeling Approaches for Discrete Event Simulations With Competing Risks Based on Censored Individual Patient Data
T2 - A Simulation Study and Illustration in Colorectal Cancer
AU - Degeling, Koen
AU - IJzerman, Maarten J.
AU - Groothuis-Oudshoorn, Catharina G.M.
AU - Franken, Mira D.
AU - Koopman, Miriam
AU - Clements, Mark S.
AU - Koffijberg, Hendrik
N1 - Funding Information:
Funding/Support: The authors received no financial support for this research.
Publisher Copyright:
© 2021 International Society for Pharmacoeconomics and Outcomes Research, Inc. Published by Elsevier Inc.
PY - 2022/1
Y1 - 2022/1
N2 - OBJECTIVES: This study aimed to provide detailed guidance on modeling approaches for implementing competing events in discrete event simulations based on censored individual patient data (IPD).METHODS: The event-specific distributions (ESDs) approach sampled times from event-specific time-to-event distributions and simulated the first event to occur. The unimodal distribution and regression approach sampled a time from a combined unimodal time-to-event distribution, representing all events, and used a (multinomial) logistic regression model to select the event to be simulated. A simulation study assessed performance in terms of relative absolute event incidence difference and relative entropy of time-to-event distributions for different types and levels of right censoring, numbers of events, distribution overlap, and sample sizes. Differences in cost-effectiveness estimates were illustrated in a colorectal cancer case study.RESULTS: Increased levels of censoring negatively affected the modeling approaches' performance. A lower number of competing events and higher overlap of distributions improved performance. When IPD were censored at random times, ESD performed best. When censoring occurred owing to a maximum follow-up time for 2 events, ESD performed better for a low level of censoring (ie, 10%). For 3 or 4 competing events, ESD better represented the probabilities of events, whereas unimodal distribution and regression better represented the time to events. Differences in cost-effectiveness estimates, both compared with no censoring and between approaches, increased with increasing censoring levels.CONCLUSIONS: Modelers should be aware of the different modeling approaches available and that selection between approaches may be informed by data characteristics. Performing and reporting extensive validation efforts remains essential to ensure IPD are appropriately represented.
AB - OBJECTIVES: This study aimed to provide detailed guidance on modeling approaches for implementing competing events in discrete event simulations based on censored individual patient data (IPD).METHODS: The event-specific distributions (ESDs) approach sampled times from event-specific time-to-event distributions and simulated the first event to occur. The unimodal distribution and regression approach sampled a time from a combined unimodal time-to-event distribution, representing all events, and used a (multinomial) logistic regression model to select the event to be simulated. A simulation study assessed performance in terms of relative absolute event incidence difference and relative entropy of time-to-event distributions for different types and levels of right censoring, numbers of events, distribution overlap, and sample sizes. Differences in cost-effectiveness estimates were illustrated in a colorectal cancer case study.RESULTS: Increased levels of censoring negatively affected the modeling approaches' performance. A lower number of competing events and higher overlap of distributions improved performance. When IPD were censored at random times, ESD performed best. When censoring occurred owing to a maximum follow-up time for 2 events, ESD performed better for a low level of censoring (ie, 10%). For 3 or 4 competing events, ESD better represented the probabilities of events, whereas unimodal distribution and regression better represented the time to events. Differences in cost-effectiveness estimates, both compared with no censoring and between approaches, increased with increasing censoring levels.CONCLUSIONS: Modelers should be aware of the different modeling approaches available and that selection between approaches may be informed by data characteristics. Performing and reporting extensive validation efforts remains essential to ensure IPD are appropriately represented.
KW - censoring
KW - competing events
KW - competing risks
KW - discrete event simulation
KW - modeling
KW - survival analysis
UR - http://www.scopus.com/inward/record.url?scp=85114668650&partnerID=8YFLogxK
U2 - 10.1016/j.jval.2021.07.016
DO - 10.1016/j.jval.2021.07.016
M3 - Article
C2 - 35031089
AN - SCOPUS:85114668650
SN - 1098-3015
VL - 25
SP - 104
EP - 115
JO - Value in Health
JF - Value in Health
IS - 1
ER -