A Transformer-Based Framework for Counterfactual Estimation of Antihypertensive Treatment Effect on COVID-19 Infection Risk - A Proof-of-Concept Study
American Journal of Hypertension · 2025
DOI: 10.1093/ajh/hpaf055 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Hypertension, 2025. Verfasst von Tran Q B Tran und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Cardiovascular and Metabolic Health, University of Glasgow, Glasgow, UK. Hauptthemen laut MEDLINE: COVID-19, Antihypertensive Agents, Hypertension, Neural Networks, Computer. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Transformer-based neural networks excel in modelling high-dimensional, time-series data with complex dependencies. This proof-of-concept study applies a transformer-X-learner framework to estimate treatment effects using real-world data, using antihypertensive drug exposure and COVID-19 risk as an exemplar.
Methods
We conducted a case-control study of 303,220 NHS Greater Glasgow and Clyde patients aged ≥ 40 years during the first two COVID-19 pandemic waves. Using a transformer-X-learner framework that incorporated temporal patterns in medication usage and comorbidities, we controlled for confounding effects and estimated individual and average treatment effects ACEIs, beta-blockers (BBs), calcium channel blockers (CCBs), thiazides (THZs), and statins on 180-day SARS-CoV-2 infection risk.
Results
The transformer-X-learner framework outperformed traditional approaches, achieving an F1 score of 0.82 and area under the precision-recall curve (AUPRC) of 0.78. ACEIs showed a negligible overall impact on COVID-19 risk (ATE: 0.97%±5.5), while BBs (-8.3%±7.3%) and CCBs (-9.7%±8.1%) were protective. Statins (3.5%±6.1%) and THZs (4.3%±10.8%) showed slight increases in risk. Treatment effects were consistent across age, gender, and socioeconomic categories.
Conclusions
ACEIs do not substantially increase the risk of COVID-19 infection while the protective effects of BBs and CCBs warrant further investigation. This study highlights the potential of transformer-based causal inference models as a powerful tool for evaluating treatment safety and efficacy in complex healthcare scenarios.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Cardiovascular and Metabolic Health, University of Glasgow, Glasgow, UK.
- Queen Elizabeth University Hospital, Glasgow, UK.
- School of Health and Wellbeing, University of Glasgow, Glasgow, UK.
- University of Pittsburgh School of Medicine, Pittsburgh, PA, USA.
ORCID-Profile: Tran Q B Tran, Shyam Visweswaran, Sandosh Padmanabhan
Zitieren
APA
Tran, T. Q. B., Lip, S., Wu, H., Visweswaran, S., Pell, J. P., & Padmanabhan, S. (2025). A Transformer-Based Framework for Counterfactual Estimation of Antihypertensive Treatment Effect on COVID-19 Infection Risk - A Proof-of-Concept Study. American Journal of Hypertension. https://doi.org/10.1093/ajh/hpaf055
Vancouver
Tran TQB, Lip S, Wu H, Visweswaran S, Pell JP, Padmanabhan S. A Transformer-Based Framework for Counterfactual Estimation of Antihypertensive Treatment Effect on COVID-19 Infection Risk - A Proof-of-Concept Study. American Journal of Hypertension. 2025. doi:10.1093/ajh/hpaf055
BibTeX
@article{Tran2025,
author = {Tran, Tran Q B and Lip, Stefanie and Wu, Honghan and Visweswaran, Shyam and Pell, Jill P and Padmanabhan, Sandosh},
title = {A Transformer-Based Framework for Counterfactual Estimation of Antihypertensive Treatment Effect on COVID-19 Infection Risk - A Proof-of-Concept Study},
journal = {American Journal of Hypertension},
year = {2025},
doi = {10.1093/ajh/hpaf055}
}
EUVIMED