|
Activity Number:
|
281
- New Methods with Applications in Mental Health Statistics
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 9, 2022 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Mental Health Statistics Section
|
|
Abstract #323251
|
|
|
Title:
|
Targeted Learning in Observational Studies with Multi-Level Treatments: An Evaluation of Antipsychotic Drug Treatment Safety for Patients with Serious Mental Illness
|
|
Author(s):
|
Jason Poulos* and Marcela Horvitz-Lennon and Katya Zelevinsky and Sharon-Lise Normand and Thomas Huijskens and Pooja Tyagi and Jiaju Yan and Jordi Diaz and Tudor Cristea-platon
|
|
Companies:
|
Harvard Medical School and The RAND Corporation and Harvard Medical School and Harvard Medical School and Quantum Black and Quantum Black and Quantum Black and Quantum Black and Quantum Black
|
|
Keywords:
|
machine learning;
multi-valued treatments;
overlap;
serious mental illness;
target minimum-loss based estimation
|
|
Abstract:
|
We investigate estimation of causal effects of multiple competing (multi-valued) treatments in the absence of randomization. Our work is motivated by an intention-to-treat study of the relative metabolic risk of assignment to one of six commonly prescribed antipsychotic drugs in a cohort of adults with serious mental illnesses. Doubly-robust estimators of multi-level treatment effects with observational data, such as targeted minimum loss-based estimation (TMLE), require that either the treatment model or outcome model is correctly specified to ensure consistent estimation. Common TMLE implementations estimate treatment probabilities using multiple binomial regressions rather than a single multinomial regression and model pairwise comparisons or marginal means univariately. We combine TMLE with machine learning to jointly estimate treatment contrasts in the overall sample and for patient subgroups. In simulation experiments, our implementation achieves superior coverage probability relative to the binomial implementation. An evaluation of the causal effects of six antipsychotic drugs on the risk of diabetes or death illustrates our approach.
|
Authors who are presenting talks have a * after their name.
