Targeted-BEHRT: Deep learning for observational causal inference on longitudinal electronic health records

TL;DR

This paper introduces Targeted-BEHRT, a deep learning model using Transformer architecture and doubly robust estimation to improve causal inference from electronic health records, especially in complex, high-dimensional data settings.

Contribution

The paper develops a novel Transformer-based model, Targeted-BEHRT, for causal inference on EHR data, demonstrating improved accuracy over benchmarks in estimating risk ratios.

Findings

Targeted-BEHRT outperforms benchmarks in estimating risk ratios.

The model maintains accuracy even with limited data.

It successfully captures the null causal association between antihypertensives and cancer.

Abstract

Observational causal inference is useful for decision making in medicine when randomized clinical trials (RCT) are infeasible or non generalizable. However, traditional approaches fail to deliver unconfounded causal conclusions in practice. The rise of "doubly robust" non-parametric tools coupled with the growth of deep learning for capturing rich representations of multimodal data, offers a unique opportunity to develop and test such models for causal inference on comprehensive electronic health records (EHR). In this paper, we investigate causal modelling of an RCT-established null causal association: the effect of antihypertensive use on incident cancer risk. We develop a dataset for our observational study and a Transformer-based model, Targeted BEHRT coupled with doubly robust estimation, we estimate average risk ratio (RR). We compare our model to benchmark statistical and deep learning models for causal inference in multiple experiments on semi-synthetic derivations of our dataset with various types and intensities of confounding. In order to further test the reliability of our approach, we test our model on situations of limited data. We find that our model provides more accurate estimates of RR (least sum absolute error from ground truth) compared to benchmarks for risk ratio estimation on high-dimensional EHR across experiments. Finally, we apply our model to investigate the original case study: antihypertensives' effect on cancer and demonstrate that our model generally captures the validated null association.