|Title||Optimal two-stage dynamic treatment regimes from a classification perspective with censored survival data.|
|Publication Type||Journal Article|
|Year of Publication||2018|
|Authors||Hager, Rebecca, Anastasios A. Tsiatis, and Marie Davidian|
|Date Published||2018 Dec|
|Keywords||Acute Disease, Algorithms, Biometry, Computer Simulation, Decision Support Techniques, Humans, Leukemia, Outcome Assessment, Health Care, Randomized Controlled Trials as Topic, Support Vector Machine, Survival Analysis|
Clinicians often make multiple treatment decisions at key points over the course of a patient's disease. A dynamic treatment regime is a sequence of decision rules, each mapping a patient's observed history to the set of available, feasible treatment options at each decision point, and thus formalizes this process. An optimal regime is one leading to the most beneficial outcome on average if used to select treatment for the patient population. We propose a method for estimation of an optimal regime involving two decision points when the outcome of interest is a censored survival time, which is based on maximizing a locally efficient, doubly robust, augmented inverse probability weighted estimator for average outcome over a class of regimes. By casting this optimization as a classification problem, we exploit well-studied classification techniques such as support vector machines to characterize the class of regimes and facilitate implementation via a backward iterative algorithm. Simulation studies of performance and application of the method to data from a sequential, multiple assignment randomized clinical trial in acute leukemia are presented.
|Original Publication||Optimal two-stage dynamic treatment regimes from a classification perspective with censored survival data.|
|PubMed Central ID||PMC6240504|
|Grant List||P01 CA142538 / CA / NCI NIH HHS / United States |
R01 HL118336 / HL / NHLBI NIH HHS / United States
U10 CA180821 / CA / NCI NIH HHS / United States
Optimal two-stage dynamic treatment regimes from a classification perspective with censored survival data.