IGC-Net for conditional average potential outcome estimation over time

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hess, Konstantin, Frauen, Dennis, Melnychuk, Valentyn, Feuerriegel, Stefan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917277008396288
author Hess, Konstantin
Frauen, Dennis
Melnychuk, Valentyn
Feuerriegel, Stefan
author_facet Hess, Konstantin
Frauen, Dennis
Melnychuk, Valentyn
Feuerriegel, Stefan
contents Estimating potential outcomes for treatments over time based on observational data is important for personalized decision-making in medicine. However, many existing methods for this task fail to properly adjust for time-varying confounding and thus yield biased estimates. There are only a few neural methods with proper adjustments, but these have inherent limitations (e.g., division by propensity scores that are often close to zero), which result in poor performance. As a remedy, we introduce the iterative G-computation network (IGC-Net). Our IGC-Net is a novel, neural end-to-end model which adjusts for time-varying confounding in order to estimate conditional average potential outcomes (CAPOs) over time. Specifically, our IGC-Net is the first neural model to perform fully regression-based iterative G-computation for CAPOs in the time-varying setting. We evaluate the effectiveness of our IGC-Net across various experiments. In sum, this work represents a significant step towards personalized decision-making from electronic health records.
format Preprint
id arxiv_https___arxiv_org_abs_2405_21012
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle IGC-Net for conditional average potential outcome estimation over time
Hess, Konstantin
Frauen, Dennis
Melnychuk, Valentyn
Feuerriegel, Stefan
Machine Learning
Methodology
Estimating potential outcomes for treatments over time based on observational data is important for personalized decision-making in medicine. However, many existing methods for this task fail to properly adjust for time-varying confounding and thus yield biased estimates. There are only a few neural methods with proper adjustments, but these have inherent limitations (e.g., division by propensity scores that are often close to zero), which result in poor performance. As a remedy, we introduce the iterative G-computation network (IGC-Net). Our IGC-Net is a novel, neural end-to-end model which adjusts for time-varying confounding in order to estimate conditional average potential outcomes (CAPOs) over time. Specifically, our IGC-Net is the first neural model to perform fully regression-based iterative G-computation for CAPOs in the time-varying setting. We evaluate the effectiveness of our IGC-Net across various experiments. In sum, this work represents a significant step towards personalized decision-making from electronic health records.
title IGC-Net for conditional average potential outcome estimation over time
topic Machine Learning
Methodology
url https://arxiv.org/abs/2405.21012