Natural Language Processing for the Identification of Silent Brain Infarcts From Neuroimaging Reports

Abstract

Background Silent brain infarction (SBI) is defined as the presence of 1 or more brain lesions, presumed to be because of vascular occlusion, found by neuroimaging (magnetic resonance imaging or computed tomography) in patients without clinical manifestations of stroke. It is more common than stroke and can be detected in 20% of healthy elderly people. Early detection of SBI may mitigate the risk of stroke by offering preventative treatment plans. Natural language processing (NLP) techniques offer an opportunity to systematically identify SBI cases from electronic health records (EHRs) by extracting, normalizing, and classifying SBI-related incidental findings interpreted by radiologists from neuroimaging reports. Objective This study aimed to develop NLP systems to determine individuals with incidentally discovered SBIs from neuroimaging reports at 2 sites: Mayo Clinic and Tufts Medical Center. Methods Both rule-based and machine learning approaches were adopted in developing the NLP system. The rule-based system was implemented using the open source NLP pipeline MedTagger, developed by Mayo Clinic. Features for rule-based systems, including significant words and patterns related to SBI, were generated using pointwise mutual information. The machine learning models adopted convolutional neural network (CNN), random forest, support vector machine, and logistic regression. The performance of the NLP algorithm was compared with a manually created gold standard. The gold standard dataset includes 1000 radiology reports randomly retrieved from the 2 study sites (Mayo and Tufts) corresponding to patients with no prior or current diagnosis of stroke or dementia. 400 out of the 1000 reports were randomly sampled and double read to determine interannotator agreements. The gold standard dataset was equally split to 3 subsets for training, developing, and testing. Results Among the 400 reports selected to determine interannotator agreement, 5 reports were removed due to invalid scan types. The interannotator agreements across Mayo and Tufts neuroimaging reports were 0.87 and 0.91, respectively. The rule-based system yielded the best performance of predicting SBI with an accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 0.991, 0.925, 1.000, 1.000, and 0.990, respectively. The CNN achieved the best score on predicting white matter disease (WMD) with an accuracy, sensitivity, specificity, PPV, and NPV of 0.994, 0.994, 0.994, 0.994, and 0.994, respectively. Conclusions We adopted a standardized data abstraction and modeling process to developed NLP techniques (rule-based and machine learning) to detect incidental SBIs and WMDs from annotated neuroimaging reports. Validation statistics suggested a high feasibility of detecting SBIs and WMDs from EHRs using NLP.

Assessment of the impact of EHR heterogeneity for clinical research through a case study of silent brain infarction

“…A case studythe ESPRESSO study This ESPRESSO study is an EHR-based study aiming to estimate the comparative effectiveness of preventive therapies on the risk of future stroke and dementia in patients with incidentally-discovered brain infraction [38,42]. The study has been approved by the Mayo Clinic and Tufts Medical Center institutional review boards.…”

Deep learning for brain disorders: from data processing to disease treatment

“…Classification of epileptic subjects versus HC has been addressed by Aoe et al [171] who built a CNN called M-Net from magnetoencephalography signals. Fu et al [172] performed natural language processing by using a CNN to detect individuals with silent brain infarction using radiological reports, as early detection can be useful for stroke prevention. Using different features extracted from functional MRI data, Yang et al [173] proposed to distinguish between migraine patients and healthy controls (but also between two subtypes of migraine) using an Inception CNN.…”

Desiderata for delivering NLP to accelerate healthcare AI advancement and a Mayo Clinic NLP-as-a-service implementation

“…Through iterative refinement conducted by a neurologist and neuroradiologist, 36 SBI-related terms were generated and grouped into three semantic concepts. 16…”