# Targeted Learning with Daily EHR Data

## TL;DR

This paper develops a scalable targeted learning method using large-scale EHR data to evaluate the impact of different interval lengths on causal inference in dynamic treatment studies.

## Contribution

It introduces a novel long-format TMLE implementation and demonstrates its application to daily EHR data for causal effect estimation.

## Key findings

- Longer intervals reduce computational cost but may affect inference accuracy.
- The proposed method efficiently handles large EHR datasets with high granularity.
- Different interval lengths yield comparable causal effect estimates, informing practical analysis choices.

## Abstract

Electronic health records (EHR) data provide a cost and time-effective opportunity to conduct cohort studies of the effects of multiple time-point interventions in the diverse patient population found in real-world clinical settings. Because the computational cost of analyzing EHR data at daily (or more granular) scale can be quite high, a pragmatic approach has been to partition the follow-up into coarser intervals of pre-specified length. Current guidelines suggest employing a 'small' interval, but the feasibility and practical impact of this recommendation has not been evaluated and no formal methodology to inform this choice has been developed. We start filling these gaps by leveraging large-scale EHR data from a diabetes study to develop and illustrate a fast and scalable targeted learning approach that allows to follow the current recommendation and study its practical impact on inference. More specifically, we map daily EHR data into four analytic datasets using 90, 30, 15 and 5-day intervals. We apply a semi-parametric and doubly robust estimation approach, the longitudinal TMLE, to estimate the causal effects of four dynamic treatment rules with each dataset, and compare the resulting inferences. To overcome the computational challenges presented by the size of these data, we propose a novel TMLE implementation, the 'long-format TMLE', and rely on the latest advances in scalable data-adaptive machine-learning software, xgboost and h2o, for estimation of the TMLE nuisance parameters.