首页 > AI前沿 > Artificial intelligence surrogates for treatment effect estimation with before-and-after data

Artificial intelligence surrogates for treatment effect estimation with before-and-after data

arXiv机器学习 2026-09-23 08:34 4 阅读 查看原文

Estimating the causal effects of medical treatments is difficult when clinically important outcomes are costly to measure or require long follow-up.

Short-term or inexpensive surrogate outcomes offer a potential alternative, but surrogate biomarkers may be unavailable or difficult to identify.

Advances in Artificial Intelligence

Advances in artificial intelligence (AI) have enabled increasingly accurate prediction of clinical outcomes from inexpensive, high-dimensional measurements, which creates an opportunity to use AI predictions themselves as surrogates.

Framework Development

To this end, we develop a framework for estimating treatment effects from paired measurements obtained before and after treatment for each treated individual.

A pretrained AI model is applied to the before and after measurements, and our estimator compares the resulting outcome predictions.

Technical Assumptions

We characterize the technical assumptions under which this within-person contrast identifies the average treatment effect on the treated, even when clinical outcomes are never observed for treated individuals.

Prediction-Powered Inference

When these assumptions cannot be justified, we use prediction-powered inference to correct bias using a small number of observed clinical outcomes and obtain valid inference.

Experiments and Validity

Synthetic and real-world cardio-oncology experiments demonstrate the validity and accuracy of the approach.