Comparison of causal forest and regression-based approaches to evaluate treatment effect heterogeneity: an application for type 2 diabetes precision medicine

Author
A. Venkatasubramaniam
B. Mateen
B. Shields
A. Hattersley
A. Jones
S. Vollmer
J. Dennis
Keywords
Humans
*Diabetes Mellitus, Type 2/drug therapy
Glycated Hemoglobin
Cohort Studies
Precision medicine
Dipeptidyl Peptidase 4/therapeutic use
Sodium-Glucose Transporter 2/therapeutic use
Hypoglycemic Agents/therapeutic use
*Dipeptidyl-Peptidase IV Inhibitors/therapeutic use
*Sodium-Glucose Transporter 2 Inhibitors/therapeutic use
Treatment Outcome
Causal forest
Counterfactual prediction
Generalized random forests
Heterogeneous treatment effects
machine learning
Treatment effect heterogeneity
Treatment selection
Type 2 diabetes
Year of Publication
2023
Journal
BMC Med Inform Decis Mak
Volume
23
Number of Pages
110
ISBN Number
1472-6947
Accession Number
37328784
DOI
10.1186/s12911-023-02207-2