Buchumschlag

Graph neural networks for individual treatment effect estimation: methods

Individual treatment effect (ITE) estimation is an important task for personalized decision-making in clinical settings. However, the data used to train an ITE estimation model may be limited. In this case, we expect that information regarding causal connectivity within features can facilitate model...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sirazitdinov, Andrei (VerfasserIn) , Buchwald, Marcus (VerfasserIn) , Heuveline, Vincent (VerfasserIn) , Hesser, Jürgen (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 02 August 2024
In: IEEE access
Year: 2024, Jahrgang: 12, Pages: 106884-106894
ISSN:2169-3536
DOI:10.1109/ACCESS.2024.3437665
Online-Zugang:Verlag, kostenfrei, Volltext: https://doi.org/10.1109/ACCESS.2024.3437665
Verlag, kostenfrei, Volltext: http://ieeexplore.ieee.org/document/10621010
Volltext
Verfasserangaben:Andrei Sirazitdinov, Marcus Buchwald, Vincent Heuveline, and Jürgen Hesser, (Member, IEEE)
Beschreibung
Zusammenfassung:Individual treatment effect (ITE) estimation is an important task for personalized decision-making in clinical settings. However, the data used to train an ITE estimation model may be limited. In this case, we expect that information regarding causal connectivity within features can facilitate model training and thus lead to better predictions. In this study, we incorporated causal information about the connectivity within features represented by a Directed Acyclic Graph (DAG) into the problem of ITE estimation. For this purpose, we propose a novel method based on Graph Neural Networks (GNN). Our results show that the proposed approach performs comparably to the current state-of-the-art methods on existing datasets. Using an artificial dataset, we demonstrate the potential advantages of using real graphs responsible for the data generation process over empty graphs with no edges. These advantages are particularly evident for datasets with limited training sizes and correctly defined DAGs. These findings highlight the potential of GNNs in personalized medicine for improving the assessment of individual treatment effects.
Beschreibung:Gesehen am 22.10.2024
Beschreibung:Online Resource
ISSN:2169-3536
DOI:10.1109/ACCESS.2024.3437665

Ähnliche Einträge