How essential are unstructured clinical narratives and information fusion to clinical trial recruitment?

TL;DR

This paper demonstrates that unstructured clinical narratives are crucial for accurately determining patient eligibility in clinical trial recruitment, especially when structured data alone is insufficient.

Contribution

The study empirically validates the importance of unstructured data and information fusion in resolving clinical trial eligibility criteria, highlighting the need for temporal reasoning.

Findings

Unstructured data resolves 59% of CLL trial criteria.

Unstructured data resolves 77% of prostate cancer trial criteria.

Temporal reasoning is essential for criteria with temporal constraints.

Abstract

Electronic health records capture patient information using structured controlled vocabularies and unstructured narrative text. While structured data typically encodes lab values, encounters and medication lists, unstructured data captures the physician's interpretation of the patient's condition, prognosis, and response to therapeutic intervention. In this paper, we demonstrate that information extraction from unstructured clinical narratives is essential to most clinical applications. We perform an empirical study to validate the argument and show that structured data alone is insufficient in resolving eligibility criteria for recruiting patients onto clinical trials for chronic lymphocytic leukemia (CLL) and prostate cancer. Unstructured data is essential to solving 59% of the CLL trial criteria and 77% of the prostate cancer trial criteria. More specifically, for resolving eligibility criteria with temporal constraints, we show the need for temporal reasoning and information integration with medical events within and across unstructured clinical narratives and structured data.