Estimating the Conditional Average Treatment Effects for Time-to-Event Outcome with Competing Risks
Abstract Number:
3735
Submission Type:
Contributed Abstract
Contributed Abstract Type:
Speed
Participants:
Runjia Li (1), Chung-Chou Chang (1)
Institutions:
(1) University of Pittsburgh, N/A
Co-Author:
First Author:
Presenting Author:
Abstract Text:
In recent years, precision treatment strategies have gained significant attention in medical research, which is particularly critical for life-threatening conditions like sepsis among intensive care unit (ICU) patients. In this study, we introduce a novel framework for estimating the conditional average treatment effects (CATE) in time-to-event data with competing risks. Our approach, which is based on cumulative incidence functions and targeted maximum likelihood estimation, achieves both asymptotic efficiency and double robustness. We provide theoretical proofs to support these properties and subsequently confirm them through simulations. We apply the proposed the proposed method to estimate the CATE of steroid in shortening the ICU discharge time of sepsis patients, considering death as a competing event. Our work identifies patients who could benefit from the steroid treatment and those who might be at risk for potential harm, thereby providing valuable insights for optimizing personalized treatment strategies on ICU patients with sepsis.
Keywords:
Causal inference|Competing risks|Conditional average treatment effect|Efficient influence function|Survival Analysis|Targeted maximum likelihood estimation
Sponsors:
Lifetime Data Science Section
Tracks:
Miscellaneous
Can this be considered for alternate subtype?
No
Are you interested in volunteering to serve as a session chair?
Yes
I have read and understand that JSM participants must abide by the Participant Guidelines.
Yes
I understand that JSM participants must register and pay the appropriate registration fee by June 1, 2024. The registration fee is non-refundable.
I understand
You have unsaved changes.