Assessing the properties of patient-specific treatment effect estimates from causal forest algorithms under essential heterogeneity

Background Treatment variation from observational data has been used to estimate patient-specific treatment effects. Causal Forest Algorithms (CFAs) developed for this task have unknown properties when treatment effect heterogeneity from unmeasured patient factors influences treatment choice – essen...

Full description

Saved in:
Bibliographic Details
Published in:BMC medical research methodology Vol. 24; no. 1; pp. 66 - 15
Main Authors: Brooks, John M., Chapman, Cole G., Chen, Brian K., Floyd, Sarah B., Hikmet, Neset
Format: Journal Article
Language:English
Published: London BioMed Central 13.03.2024
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Algorithms
Analysis
Bias
Causal Forest Algorithm (CFA)
Causal Inference and Observational Data
Causality
Computer Simulation
Computer-generated environments
Decision making
Estimates
Health Sciences
Humans
Leung Ping-kwan
Linear probability estimators
Machine learning
Medical research
Medicare
Medicine
Medicine & Public Health
Medicine, Experimental
Patient Selection
Patients
Simulation
Simulation modeling
Somatotropin releasing hormone
Statistical Theory and Methods
Statistics for Life Sciences
Surgery
Theory of Medicine/Bioethics
Treatment effect estimation
Treatment Effect Heterogeneity
Treatment outcome
United States
Causal Forest Algorithm (CFA)
Simulation modeling
Treatment effect estimation
Linear probability estimators
Machine learning
ISSN:1471-2288, 1471-2288
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Treatment variation from observational data has been used to estimate patient-specific treatment effects. Causal Forest Algorithms (CFAs) developed for this task have unknown properties when treatment effect heterogeneity from unmeasured patient factors influences treatment choice – essential heterogeneity . Methods We simulated eleven populations with identical treatment effect distributions based on patient factors. The populations varied in the extent that treatment effect heterogeneity influenced treatment choice. We used the generalized random forest application (CFA-GRF) to estimate patient-specific treatment effects for each population. Average differences between true and estimated effects for patient subsets were evaluated. Results CFA-GRF performed well across the population when treatment effect heterogeneity did not influence treatment choice. Under essential heterogeneity, however, CFA-GRF yielded treatment effect estimates that reflected true treatment effects only for treated patients and were on average greater than true treatment effects for untreated patients. Conclusions Patient-specific estimates produced by CFAs are sensitive to why patients in real-world practice make different treatment choices. Researchers using CFAs should develop conceptual frameworks of treatment choice prior to estimation to guide estimate interpretation ex post .
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1471-2288
1471-2288
DOI:10.1186/s12874-024-02187-5