Event-based clinical findings extraction from radiology reports with pre-trained language model

TL;DR

This paper introduces a new annotated corpus of radiology reports and employs BERT-based models to extract detailed clinical findings, demonstrating high accuracy and cross-institutional generalizability for automated semantic representation of radiological data.

Contribution

It presents a novel event-based annotation schema for radiology reports and applies state-of-the-art deep learning models to extract detailed clinical findings with high performance.

Findings

Achieved over 90% F1 for finding triggers

Attained 72-85% F1 for argument roles

Model generalized well to external MIMIC-CXR data

Abstract

Radiology reports contain a diverse and rich set of clinical abnormalities documented by radiologists during their interpretation of the images. Comprehensive semantic representations of radiological findings would enable a wide range of secondary use applications to support diagnosis, triage, outcomes prediction, and clinical research. In this paper, we present a new corpus of radiology reports annotated with clinical findings. Our annotation schema captures detailed representations of pathologic findings that are observable on imaging ("lesions") and other types of clinical problems ("medical problems"). The schema used an event-based representation to capture fine-grained details, including assertion, anatomy, characteristics, size, count, etc. Our gold standard corpus contained a total of 500 annotated computed tomography (CT) reports. We extracted triggers and argument entities using two state-of-the-art deep learning architectures, including BERT. We then predicted the linkages between trigger and argument entities (referred to as argument roles) using a BERT-based relation extraction model. We achieved the best extraction performance using a BERT model pre-trained on 3 million radiology reports from our institution: 90.9%-93.4% F1 for finding triggers 72.0%-85.6% F1 for arguments roles. To assess model generalizability, we used an external validation set randomly sampled from the MIMIC Chest X-ray (MIMIC-CXR) database. The extraction performance on this validation set was 95.6% for finding triggers and 79.1%-89.7% for argument roles, demonstrating that the model generalized well to the cross-institutional data with a different imaging modality. We extracted the finding events from all the radiology reports in the MIMIC-CXR database and provided the extractions to the research community.