Primary Submission Category: Machine Learning and Causal Inference
Leveraging text data for causal inference using electronic health records
Authors: Aaron Kaufman, Reagan Mozer, Leo Celi,
Presenting Author: Luke Miratrix*
Text is a ubiquitous component of medical data, containing valuable information about patient characteristics and care that are often missing from structured chart data. Despite this richness, it is rarely used in clinical research, owing partly to its complexity.
Using a large database of patient records and treatment histories accompanied by extensive notes by attendant physicians and nurses, we show how text data improve research in all stages, from conception and design to analysis and interpretation, with minimal additional effort.
We focus on studies using matching for causal inference.
We augment a classic matching analysis by incorporating text in three ways: by using text to supplement a multiple imputation procedure, we improve the fidelity of imputed values to handle missing data; by incorporating text in the matching stage, we improve covariate balance; and by conditioning on text, we can estimate easily interpretable text-based heterogeneous treatment effects that may be stronger than those found across categories of structured covariates.
We introduce software to implement our procedures to ease their incorporation into existing workflows.
Using these techniques, we hope to expand the scope of secondary analysis of clinical data to domains where quantitative data is of poor quality or nonexistent but text is available, such as in developing countries.