LLM-Extracted Covariates for Clinical Causal Inference: Rethinking Integration Strategies

• URL: http://arxiv.org/abs/2604.16763v2
• Date: Tue, 21 Apr 2026 03:21:58 GMT
• Title: LLM-Extracted Covariates for Clinical Causal Inference: Rethinking Integration Strategies
• Abstract summary: Causal inference from electronic health records is fundamentally limited by unmeasured confounding.<n>We show how to effectively integrate latent confounders into causal estimation pipelines.
• Score: 7.5675661390024125
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Causal inference from electronic health records (EHR) is fundamentally limited by unmeasured confounding: critical clinical states such as frailty, goals of care, and mental status are documented in free-text notes but absent from structured data. Large language models can extract these latent confounders as interpretable, structured covariates, yet how to effectively integrate them into causal estimation pipelines has not been systematically studied. Using the MIMIC-IV database with 21,859 sepsis patients, we compare seven covariate-integration strategies for estimating the effect of early vasopressor initiation on 28-day mortality, spanning tabular-only baselines, traditional NLP representations, and three LLM-augmented approaches. A central finding is that not all integration strategies are equally effective: directly augmenting the propensity score model with LLM covariates achieves the best performance, while dual-caliper matching on text-derived categorical distances restricts the donor pool and degrades estimation. In semi-synthetic experiments with known ground-truth effects, LLM-augmented propensity scores reduce estimation bias from 0.0143 to 0.0003 relative to tabular-only methods, and this advantage persists under substantial simulated extraction error. On real data, incorporating LLM-extracted covariates reduces the estimated treatment effect from 0.055 to 0.027, directionally consistent with the CLOVERS randomized trial, and a doubly robust estimator yielding 0.019 confirms the robustness of this finding. Our results offer practical guidance on when and how text-derived covariates improve causal estimation in critical care.

Related papers

• Rethinking the Evaluation and Optimization of LLM-Based Social Simulation [56.18577997572273]
  We use the subjectivity coefficient to analyze how accuracy-based evaluation and hard-label training fail as subjectivity grows.<n>We construct SUBJSIM, a benchmark of 19,300 contexts covering 193 annotators and 100 subjective questions.<n>Results on SUBJSIM demonstrate the advantages of our method.
  arXiv  Detail & Related papers  (2026-08-20T06:26:03Z)
• Learning heterogeneous treatment effects under principal stratification [4.965155763091777]
  We study the identification and estimation of the conditional principal causal effects under principal ignorability.<n>We propose a novel doubly cross-fit doubly robust machine that resolves the nested nuisance structure inherent to principal stratification.
  arXiv  Detail & Related papers  (2026-06-27T20:27:17Z)
• Disentangled Double Machine Learning for Accurate Causal Effect Estimation [80.07136847623498]
  Confounding bias is a key challenge in causal effect estimation from observational data.<n>Double Machine Learning (DML) addresses this issue by estimating treatment and outcome nuisance functions.<n>DML often produces biased and unstable estimates in highdimensional or finite-sample scenarios.<n>We propose Disentangled Double Machine Learning (DDML), a novel algorithm that integrates two key strategies.
  arXiv  Detail & Related papers  (2026-05-24T01:40:43Z)
• Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation [0.0]
  We propose a two-stage pipeline for treatment effect estimation from incomplete longitudinal EHRs.<n>CaulFlow-T, a directed acyclic graph (DAG)-constrained normalizing flow with long short-term memory (LSTM)-encoded patient history.<n>CaulFlow-T performs exact invertible counterfactual inference, avoiding approximation errors from variational inference and separating confounding through explicit causal structure.
  arXiv  Detail & Related papers  (2026-05-06T16:53:08Z)
• Predicting Post-Traumatic Epilepsy from Clinical Records using Large Language Model Embeddings [1.5481419663066267]
  Post-traumatic epilepsy (PTE) is a debilitating neurological disorder that develops after traumatic brain injury (TBI)<n>We developed an automated PTE prediction framework that implements pretrained large language models (LLMs) as fixed feature extractors to encode clinical records.
  arXiv  Detail & Related papers  (2026-04-16T02:24:24Z)
• PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation [51.96735866702332]
  PREBA is a retrieval-augmented framework that integrates PCA-weighted retrieval and Bayesian averaging aggregation.<n> PREBA significantly improves performance-for instance, reducing MAE by up to 40% and raising R2 from -0.13 to 0.62 over zero-shot inference.
  arXiv  Detail & Related papers  (2026-02-27T07:19:23Z)
• Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering [94.37535002230504]
  We develop a training-free, inference-time control framework termed Semantically Decoupled Latent Steering.<n>Our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition.<n>We show that our approach significantly reduces the probability of historical hallucinations.
  arXiv  Detail & Related papers  (2026-02-27T04:49:01Z)
• Assumption-Lean Post-Integrated Inference with Surrogate Control Outcomes [6.448728765953916]
  We introduce a robust post-integrated inference (PII) method that adjusts for latent heterogeneity using control outcomes.<n>We develop semiparametric inference on projected direct effect estimands, accounting for hidden mediators, confounders, and moderators.<n>The proposed doubly robust estimators are consistent and efficient under minimal assumptions and potential misspecification.
  arXiv  Detail & Related papers  (2024-10-07T12:52:38Z)
• B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding [51.74479522965712]
  We propose a meta-learner called the B-Learner, which can efficiently learn sharp bounds on the CATE function under limits on hidden confounding. We prove its estimates are valid, sharp, efficient, and have a quasi-oracle property with respect to the constituent estimators under more general conditions than existing methods.
  arXiv  Detail & Related papers  (2023-04-20T18:07:19Z)
• Robust and Agnostic Learning of Conditional Distributional Treatment Effects [44.31792000298105]
  We provide a new robust and model-agnostic methodology for learning the conditional DTE (CDTE) for a class of problems.<n>Our method is model-agnostic in that it can provide the best projection of CDTE onto the regression model class.<n>We investigate the behavior of our proposal in simulations, as well as in a case study of 401(k) eligibility effects on wealth.
  arXiv  Detail & Related papers  (2022-05-23T17:40:31Z)
• Treatment Effect Risk: Bounds and Inference [58.442274475425144]
  Since the average treatment effect measures the change in social welfare, even if positive, there is a risk of negative effect on, say, some 10% of the population. In this paper we consider how to nonetheless assess this important risk measure, formalized as the conditional value at risk (CVaR) of the ITE distribution. Some bounds can also be interpreted as summarizing a complex CATE function into a single metric and are of interest independently of being a bound.
  arXiv  Detail & Related papers  (2022-01-15T17:21:26Z)
• Estimating heterogeneous survival treatment effect in observational data using machine learning [9.951103976634407]
  Methods for estimating heterogeneous treatment effect in observational data have largely focused on continuous or binary outcomes. Using flexible machine learning methods in the counterfactual framework is a promising approach to address challenges due to complex individual characteristics.
  arXiv  Detail & Related papers  (2020-08-17T01:02:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.