How Effective Are Machine Learning and Doubly Robust Estimators in Incorporating High‐Dimensional Proxies to Reduce Residual Confounding?
Pharmacoepidemiology and Drug Safety · 2025
DOI: 10.1002/pds.70155 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pharmacoepidemiology and Drug Safety, 2025. Verfasst von Mohammad Ehsanul Karim und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Population and Public Health, University of British Columbia, Vancouver, British Columbia, Canada. Hauptthemen laut MEDLINE: Machine Learning, Observational Studies as Topic. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, MEK's Natural Sciences and Engineering Research Council of Canada (NSERC).
Abstract (Originalsprache)
Background
Residual confounding presents a persistent challenge in observational studies, particularly in high‐dimensional settings. High‐dimensional proxy adjustment methods, such as the high‐dimensional propensity score (hdPS), are widely used to address confounding bias by incorporating proxies for unmeasured confounders. Extensions of hdPS have integrated machine learning, such as LASSO and super learner (SL), and doubly robust estimators, such as targeted maximum likelihood estimation (TMLE). However, the comparative performance of these methods, especially under different learner configurations and high‐dimensional proxies, remains unclear.
Method
We conducted plasmode simulations to evaluate the performance of standard methods, SL, TMLE, and double cross‐fit TMLE (DC‐TMLE) under varying exposure and outcome prevalence scenarios. Learner libraries included: 1 learner (logistic regression), 3 learners (logistic regression, MARS, and LASSO), and 4 learners (adding XGBoost, a non‐Donsker learner). Metrics included bias, coverage, and variability.
Results
Methods without proxies exhibited the highest bias and poorest coverage, highlighting the critical role of proxies in confounding adjustment. Standard methods incorporating high‐dimensional proxies showed robust performance, achieving low bias and near‐nominal coverage. TMLE and DC‐TMLE reduced bias but exhibited worse coverage compared to standard methods, particularly with larger learner libraries. Notably, DC‐TMLE, expected to address under‐coverage issues, failed to perform adequately in high‐dimensional settings with non‐Donsker learners, further emphasizing the instability introduced by complex libraries.
Conclusion
Our findings underscore the utility of high‐dimensional proxies in standard methods and the importance of tailoring learner configurations in SL and TMLE to ensure reliable confounding adjustment in high‐dimensional contexts.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Population and Public Health, University of British Columbia, Vancouver, British Columbia, Canada.
- Centre for Advancing Health Outcomes, University of British Columbia, Vancouver, British Columbia, Canada.
- Department of Statistics, University of British Columbia, Vancouver, British Columbia, Canada.
ORCID-Profile: Mohammad Ehsanul Karim
Förderung
- Natural Sciences and Engineering Research Council of Canada
- MEK's Natural Sciences and Engineering Research Council of Canada (NSERC)
Zitieren
APA
Karim, M. E., & Lei, Y. (2025). How Effective Are Machine Learning and Doubly Robust Estimators in Incorporating High‐Dimensional Proxies to Reduce Residual Confounding?. Pharmacoepidemiology and Drug Safety. https://doi.org/10.1002/pds.70155
Vancouver
Karim ME, Lei Y. How Effective Are Machine Learning and Doubly Robust Estimators in Incorporating High‐Dimensional Proxies to Reduce Residual Confounding?. Pharmacoepidemiology and Drug Safety. 2025. doi:10.1002/pds.70155
BibTeX
@article{Karim2025,
author = {Karim, Mohammad Ehsanul and Lei, Yang},
title = {How Effective Are Machine Learning and Doubly Robust Estimators in Incorporating High‐Dimensional Proxies to Reduce Residual Confounding?},
journal = {Pharmacoepidemiology and Drug Safety},
year = {2025},
doi = {10.1002/pds.70155}
}
EUVIMED