Search

Background Abstraction of critical data from unstructured radiologic reports using natural language processing (NLP) is a powerful tool to automate the detection of important clinical features and enhance research efforts. We present a set of NLP approaches to identify critical findings in patients with acute ischemic stroke from radiology reports of computed tomography (CT) and magnetic resonance imaging (MRI). Methods We trained machine learning classifiers to identify categorical outcomes of edema, midline shift (MLS), hemorrhagic transformation, and parenchymal hematoma, as well as rule-based systems (RBS) to identify intraventricular hemorrhage (IVH) and continuous MLS measurements within CT/MRI reports. Using a derivation cohort of 2289 reports from 550 individuals with acute middle cerebral artery territory ischemic strokes, we externally validated our models on reports from a separate institution as well as from patients with ischemic strokes in any vascular territory. Results In all data sets, a deep neural network with pretrained biomedical word embeddings (BioClinicalBERT) achieved the highest discrimination performance for binary prediction of edema (area under precision recall curve [AUPRC] > 0.94), MLS (AUPRC > 0.98), hemorrhagic conversion (AUPRC > 0.89), and parenchymal hematoma (AUPRC > 0.76). BioClinicalBERT outperformed lasso regression (p Conclusions Our study demonstrates robust performance and external validity of a core NLP tool kit for identifying both categorical and continuous outcomes of ischemic stroke from unstructured radiographic text data. Medically tailored NLP methods have multiple important big data applications, including scalable electronic phenotyping, augmentation of clinical risk prediction models, and facilitation of automatic alert systems in the hospital setting.

Huntington disease (HD) is a neurodegenerative disorder that involves preferential atrophy in the striatal complex and related subcortical nuclei. In this article, which is based on a dataset extracted from the PREDICT-HD study, we use statistical shape analysis with deformation markers obtained through "Large Deformation Diffeomorphic Metric Mapping" of cortical surfaces to highlight specific atrophy patterns in the caudate, putamen, and globus pallidus, at different prodromal stages of the disease. On the basis of the relation to cortico-basal ganglia circuitry, we propose that statistical shape analysis, along with other structural and functional imaging studies, may help expand our understanding of the brain circuitry affected and other aspects of the neurobiology of HD, and also guide the most effective strategies for intervention. © 2012 Wiley Periodicals, Inc.