Journal
BIOMETRICAL JOURNAL
Volume 64, Issue 4, Pages 805-817Publisher
WILEY
DOI: 10.1002/bimj.202100077
Keywords
causal inference; clinical decision making; electronic health record; precision medicine; text mining
Funding
- National Science Foundation [1416953, 1636840, 1734853, 1916425]
- National Institutes ofHealth [R01CA233487, R01MH121079, R01MH126137, T32GM141746, UL1TR002240]
- Direct For Computer & Info Scie & Enginr [1636840] Funding Source: National Science Foundation
- Direct For Education and Human Resources [1416953] Funding Source: National Science Foundation
- Direct For Social, Behav & Economic Scie
- Division Of Behavioral and Cognitive Sci [1734853] Funding Source: National Science Foundation
- Division Of Undergraduate Education [1416953] Funding Source: National Science Foundation
- Office of Advanced Cyberinfrastructure (OAC) [1636840] Funding Source: National Science Foundation
- Office of Advanced Cyberinfrastructure (OAC)
- Direct For Computer & Info Scie & Enginr [1916425] Funding Source: National Science Foundation
Ask authors/readers for more resources
The wide-scale adoption of electronic health records provides extensive information for precision medicine and personalized healthcare. By leveraging free-text clinical information extraction techniques, optimal dynamic treatment regimes can be estimated, allowing for individualized treatments based on patient characteristics and treatment history.
The wide-scale adoption of electronic health records (EHRs) provides extensive information to support precision medicine and personalized health care. In addition to structured EHRs, we leverage free-text clinical information extraction (IE) techniques to estimate optimal dynamic treatment regimes (DTRs), a sequence of decision rules that dictate how to individualize treatments to patients based on treatment and covariate history. The proposed IE of patient characteristics closely resembles The clinical Text Analysis and Knowledge Extraction System and employs named entity recognition, boundary detection, and negation annotation. It also utilizes regular expressions to extract numerical information. Combining the proposed IE with optimal DTR estimation, we extract derived patient characteristics and use tree-based reinforcement learning (T-RL) to estimate multistage optimal DTRs. IE significantly improved the estimation in counterfactual outcome models compared to using structured EHR data alone, which often include incomplete data, data entry errors, and other potentially unobserved risk factors. Moreover, including IE in optimal DTR estimation provides larger study cohorts and a broader pool of candidate tailoring variables. We demonstrate the performance of our proposed method via simulations and an application using clinical records to guide blood pressure control treatments among critically ill patients with severe acute hypertension. This joint estimation approach improves the accuracy of identifying the optimal treatment sequence by 14-24% compared to traditional inference without using IE, based on our simulations over various scenarios. In the blood pressure control application, we successfully extracted significant blood pressure predictors that are unobserved or partially missing from structured EHR.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available